© 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. 2710
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    names of places or geographical features

    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
    usting
    -0.82
    uggest
    -0.79
    ãĥ¼ãĤ¯
    -0.75
     guiActiveUn
    -0.75
    usted
    -0.74
    ajor
    -0.72
    endor
    -0.69
    conom
    -0.66
    erity
    -0.65
    ession
    -0.64
    POSITIVE LOGITS
     etc
    1.49
    etc
    1.09
     Lastly
    0.80
     Leilan
    0.80
     et
    0.77
     Jr
    0.76
     Laksh
    0.76
     respectively
    0.74
    ioch
    0.73
     Moroc
    0.73
    Activations Density 0.230%

    No Known Activations