© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    technical terms or actions related to specific fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluation and assessment

    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
     unanimous
    -0.63
     omission
    -0.62
     caution
    -0.57
     bombshell
    -0.56
    cluded
    -0.55
     confirmation
    -0.55
     thous
    -0.54
     acknowled
    -0.53
     guys
    -0.53
    amera
    -0.52
    POSITIVE LOGITS
     thereof
    1.08
     of
    0.81
    iru
    0.76
    Downloadha
    0.73
     abroad
    0.68
     therein
    0.68
    utic
    0.68
    utics
    0.68
    thood
    0.64
    ptin
    0.61
    Activations Density 0.706%

    No Known Activations