© 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. 7-RES-JB
    11. 11769
    Prev
    Next
    INDEX
    Explanations

    product descriptions or technical details related to devices or software

    oai_token-act-pair · gpt-3.5-turbo

    sections of text related to ratings or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.84
    boro
    -0.80
    rad
    -0.67
     footing
    -0.66
    athe
    -0.63
    bourg
    -0.60
     grid
    -0.57
     illusion
    -0.56
    burn
    -0.56
    minist
    -0.55
    POSITIVE LOGITS
    ³³³³
    0.93
    ³³³
    0.89
    Nevertheless
    0.84
    ³³³³³³³³³³³³³³³³
    0.83
    Furthermore
    0.83
    Meanwhile
    0.81
    Nonetheless
    0.81
    Lastly
    0.80
    Interestingly
    0.80
    Likewise
    0.79
    Activations Density 0.499%

    No Known Activations