© 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. 4595
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or outcomes based on specific actions or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements that begin with "if."

    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
     srfAttach
    -0.67
    ights
    -0.65
    %);
    -0.64
     GOODMAN
    -0.64
    Town
    -0.64
    Rated
    -0.61
    arling
    -0.60
     Among
    -0.59
    Ãį
    -0.58
    åĨ
    -0.58
    POSITIVE LOGITS
    fy
    1.09
     you
    0.98
     someone
    0.88
     somebody
    0.86
     anything
    0.84
     unchecked
    0.82
    soever
    0.80
    someone
    0.78
     unlucky
    0.75
     they
    0.73
    Activations Density 0.113%

    No Known Activations