© 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. 7121
    Prev
    Next
    INDEX
    Explanations

    the names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to various topics of discussion

    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
    mma
    -0.72
    aminer
    -0.70
    ixties
    -0.66
    HY
    -0.64
     Gemini
    -0.61
    aughters
    -0.61
    jri
    -0.61
    ramid
    -0.60
    itudes
    -0.60
    aunder
    -0.58
    POSITIVE LOGITS
     should
    0.64
     hadn
    0.64
     lacks
    0.62
     backers
    0.59
     programmers
    0.58
     could
    0.58
     justifies
    0.57
     writers
    0.57
     forgot
    0.56
    rats
    0.56
    Activations Density 0.420%

    No Known Activations