© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 1551
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change or transition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a change or recent developments

    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
    umbn
    -0.68
    lez
    -0.65
     Ops
    -0.63
    vec
    -0.63
     Springfield
    -0.61
    yrics
    -0.61
    comp
    -0.60
     Apostle
    -0.58
     EntityItem
    -0.58
    ``
    -0.58
    POSITIVE LOGITS
    DEN
    0.82
     unsus
    0.74
     unnoticed
    0.73
     belonged
    0.68
     dating
    0.67
    ione
    0.65
    unknown
    0.65
    í
    0.64
    inction
    0.64
     hesitated
    0.64
    Activations Density 0.066%

    No Known Activations