© 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. 3079
    Prev
    Next
    INDEX
    Explanations

    player names from sports-related texts

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

    specific names or identifiers, likely of people or entities

    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
    Þ
    -1.68
     behavi
    -1.65
    ß
    -1.47
    ô
    -1.43
    PDATE
    -1.40
     millenn
    -1.38
     referen
    -1.35
     exha
    -1.33
     eleph
    -1.32
     conflic
    -1.31
    POSITIVE LOGITS
    amina
    1.19
    ortium
    1.17
    akespe
    1.17
    indle
    1.16
    ombs
    1.16
    urnal
    1.16
    abul
    1.15
    igne
    1.15
    amph
    1.14
    yip
    1.14
    Activations Density 0.447%

    No Known Activations