© 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. 17533
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or calls to action in the form of instructions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to sharing or distributing content

    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
    zik
    -0.81
     ambassadors
    -0.68
     transition
    -0.67
     manif
    -0.66
    mbuds
    -0.66
    onite
    -0.66
    izons
    -0.66
    uka
    -0.66
    iage
    -0.65
     overpower
    -0.65
    POSITIVE LOGITS
     Become
    0.85
     CrossRef
    0.85
     PubMed
    0.83
     ¯
    0.82
     Pocket
    0.81
     Please
    0.79
     Email
    0.79
     Join
    0.77
     Learns
    0.73
     https
    0.73
    Activations Density 0.048%

    No Known Activations