© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22880
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or commands instructing to click or download

    oai_token-act-pair · gpt-3.5-turbo

    sentences that refer to accessing additional information or content

    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
     awakening
    -0.81
     revol
    -0.79
    Ļ½
    -0.77
     questioning
    -0.75
     impression
    -0.75
     footing
    -0.75
     instinct
    -0.74
     unheard
    -0.73
     unthinkable
    -0.73
     unrealistic
    -0.73
    POSITIVE LOGITS
    <|endoftext|>
    1.37
     Alternatively
    1.34
     Also
    1.24
     Additionally
    1.16
    aspx
    1.05
    pdf
    1.04
     Otherwise
    1.04
     Each
    1.02
     Afterwards
    1.01
     Downloads
    1.01
    Activations Density 0.251%

    No Known Activations