© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15177
    Prev
    Next
    INDEX
    Explanations

    phrases related to things that are frequent, usual, or ordinary

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "common" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mosp
    -0.83
    gur
    -0.76
    usalem
    -0.75
    oÄŁ
    -0.72
    forestation
    -0.72
    udging
    -0.72
    etry
    -0.70
    overe
    -0.69
    oti
    -0.69
    otiation
    -0.68
    POSITIVE LOGITS
    wealth
    1.12
     occurrences
    0.92
     occurrence
    0.87
    ality
    0.84
    alities
    0.84
     denomin
    0.80
    places
    0.79
     ancestor
    0.78
    ensical
    0.78
    Sym
    0.76
    Activations Density 0.022%

    No Known Activations