© 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. 21811
    Prev
    Next
    INDEX
    Explanations

    words related to sharing or disseminating information, such as "Read" or "Share"

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" in various contexts

    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
    ouls
    -0.68
    hower
    -0.65
     tom
    -0.63
    raint
    -0.61
    blance
    -0.60
    elli
    -0.60
    steen
    -0.60
    ħĭ
    -0.59
    atari
    -0.59
    ngth
    -0.58
    POSITIVE LOGITS
    acles
    0.77
    chard
    0.71
    acle
    0.70
     Format
    0.68
    leans
    0.65
     modify
    0.64
     suffer
    0.64
    ANGE
    0.64
    Else
    0.64
     subscribe
    0.63
    Activations Density 0.016%

    No Known Activations