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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2881
    Prev
    Next
    INDEX
    Explanations

    terms related to security breaches and achievements in sports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    notable events or entities associated with significant impact or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rall
    -0.63
    ĻĤ
    -0.63
     conduc
    -0.63
    ŃĶ
    -0.58
    pport
    -0.58
    natureconservancy
    -0.55
    ?????-
    -0.53
    oint
    -0.53
     arrang
    -0.52
     cryst
    -0.52
    POSITIVE LOGITS
     into
    2.50
    into
    2.14
     Into
    1.99
     INTO
    1.99
     onto
    1.82
     overboard
    1.07
     toward
    0.96
     towards
    0.88
     back
    0.78
     deeper
    0.78
    Activations Density 0.758%

    No Known Activations