© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37307
    Prev
    Next
    INDEX
    Explanations

    terms related to remediation and care in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.14
    0.6%
    508
    +0.11
    0.5%
    431
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.14
    0.01
    569
    +0.11
    0.01
    288
    +0.10
    0.01
    Negative Logits
    caps
    -0.63
    ulton
    -0.62
     SAS
    -0.61
    */(
    -0.60
    anwhile
    -0.60
    >>>>>>>>
    -0.58
    OVA
    -0.58
    kefeller
    -0.57
     Spice
    -0.57
     intimate
    -0.56
    POSITIVE LOGITS
    iation
    1.49
    ial
    1.39
    iated
    1.29
    iate
    1.21
    iating
    1.08
    iates
    1.02
    ially
    1.02
    iously
    1.01
    ials
    1.01
    iable
    0.98
    Activations Density 0.004%

    No Known Activations