© 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. 23037
    Prev
    Next
    INDEX
    Explanations

    words related to processing or manipulation of materials or resources

    oai_token-act-pair · gpt-3.5-turbo

    words associated with extraction and processing of resources

    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
     neigh
    -0.65
     subclass
    -0.64
     lawy
    -0.63
     nort
    -0.59
     Whe
    -0.58
     precedence
    -0.58
     Nig
    -0.58
    perty
    -0.58
     Supreme
    -0.58
     Racial
    -0.57
    POSITIVE LOGITS
    ment
    1.33
    able
    1.28
    ments
    1.25
    ables
    1.23
    ing
    1.14
    ability
    1.10
    ings
    1.04
    ation
    1.03
    MENT
    0.98
    ABLE
    0.98
    Activations Density 0.233%

    No Known Activations