© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 45946
    Prev
    Next
    INDEX
    Explanations

    phrases related to rewards and rewards systems

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.25
    1.0%
    620
    +0.13
    0.5%
    288
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.25
    0.35
    362
    +0.13
    0.18
    608
    +0.12
    0.24
    Negative Logits
    abad
    -0.88
    enium
    -0.85
    abases
    -0.81
     Ange
    -0.79
    lander
    -0.77
    obiles
    -0.77
    opic
    -0.75
     Osw
    -0.75
    head
    -0.74
     Alic
    -0.74
    POSITIVE LOGITS
     reward
    1.23
     rewarded
    1.20
     rewards
    1.16
     rewarding
    0.97
     reap
    0.90
    Reward
    0.90
     handsome
    0.87
     Reward
    0.86
     incentive
    0.86
     reinforcement
    0.85
    Activations Density 14.218%

    No Known Activations