© 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. 3306
    Prev
    Next
    INDEX
    Explanations

    mentions of specific subjects and actions with some critical or negative sentiment

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics and numerical data

    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
    76561
    -0.53
    venge
    -0.51
    PRES
    -0.50
    const
    -0.48
    aging
    -0.47
    âĹ¼
    -0.47
    tnc
    -0.47
    NetMessage
    -0.45
    shore
    -0.44
    AI
    -0.44
    POSITIVE LOGITS
    querque
    0.69
    ashtra
    0.66
    ividual
    0.65
    arij
    0.57
    emonium
    0.57
    ãĥ¼ãĥĨãĤ£
    0.57
     consists
    0.54
    allo
    0.53
     consisted
    0.53
    encies
    0.52
    Activations Density 7.081%

    No Known Activations