© 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. 1-RES-JB
    11. 11239
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific character or professional title (such as "Proctor")

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "function" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mable
    -0.75
    fig
    -0.68
     willingness
    -0.68
    RESULTS
    -0.67
    committee
    -0.65
     generous
    -0.65
    metry
    -0.64
    values
    -0.64
    TIT
    -0.64
     preference
    -0.63
    POSITIVE LOGITS
    anto
    1.17
    ctor
    1.15
    iola
    0.82
    isy
    0.81
    angelo
    0.81
    ose
    0.77
    iculture
    0.77
    osa
    0.73
    ivari
    0.73
    iatrics
    0.72
    Activations Density 0.007%

    No Known Activations