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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17009
    Prev
    Next
    INDEX
    Explanations

    the word 'third'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to third-party entities and their involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ++++++++++++++++
    -0.84
    staking
    -0.76
    UTION
    -0.71
    Money
    -0.70
    Tokens
    -0.69
    Reward
    -0.69
    immers
    -0.66
    ITED
    -0.64
    NUM
    -0.64
     Militia
    -0.63
    POSITIVE LOGITS
     baseman
    1.15
    rd
    1.09
     quarters
    0.83
     inning
    0.82
    irty
    0.81
    orne
    0.77
    uous
    0.74
    ortun
    0.74
    ulhu
    0.73
    ority
    0.73
    Activations Density 0.032%

    No Known Activations