© 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. 8-RES-JB
    11. 18484
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs indicating hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    second-person and first-person pronouns, indicating a focus on direct address or personal connection in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
    ces
    -0.93
    76561
    -0.80
    opens
    -0.76
    got
    -0.72
    edIn
    -0.68
    mining
    -0.68
    ooks
    -0.66
    started
    -0.66
    ca
    -0.66
    assemb
    -0.64
    POSITIVE LOGITS
     succeed
    1.09
     be
    1.06
     suffice
    1.03
     continue
    0.96
     survive
    0.95
     concede
    0.94
     abandon
    0.94
     accept
    0.92
     migrate
    0.92
     persist
    0.90
    Activations Density 0.077%

    No Known Activations