© 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. 6-RES-JB
    11. 830
    Prev
    Next
    INDEX
    Explanations

    text related to analysts' opinions and analyses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of analysts and their viewpoints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boats
    -0.69
    stones
    -0.67
     traumatic
    -0.67
     Tub
    -0.67
     DeL
    -0.66
    SIZE
    -0.64
    tein
    -0.64
    boat
    -0.62
     Mamm
    -0.61
    FACE
    -0.61
    POSITIVE LOGITS
     analyst
    1.08
    alyst
    0.98
     analysts
    0.82
     Analyst
    0.79
    rador
    0.76
    onite
    0.70
    roit
    0.69
    irtual
    0.68
    athering
    0.68
    igible
    0.67
    Activations Density 0.020%

    No Known Activations