© 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. 14753
    Prev
    Next
    INDEX
    Explanations

    quotes within dialogue where the speaker expresses their desire to participate in something

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" used 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
    evidence
    -0.81
    agree
    -0.72
    Edit
    -0.71
    Events
    -0.71
    enance
    -0.70
    Attempts
    -0.69
    Catal
    -0.67
    Applic
    -0.67
    Shares
    -0.67
     Actions
    -0.66
    POSITIVE LOGITS
     bunch
    1.31
     lot
    1.27
     handful
    1.12
     few
    1.09
     couple
    1.07
     piece
    1.05
     decent
    1.01
     huge
    1.00
     bit
    1.00
     nice
    1.00
    Activations Density 1.107%

    No Known Activations