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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 9930
    Prev
    Next
    INDEX
    Explanations

    words related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or entities, particularly focusing on a recurring name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hart
    -0.65
    %:
    -0.64
    hood
    -0.63
    iatrics
    -0.61
     CARE
    -0.60
    fare
    -0.58
    erest
    -0.58
    ı
    -0.58
    ³³³³
    -0.57
    jad
    -0.57
    POSITIVE LOGITS
    clerosis
    1.03
    ions
    0.96
    lav
    0.85
    ilaterally
    0.83
    ion
    0.82
    cler
    0.81
    heet
    0.77
    xual
    0.76
    orb
    0.76
    ophone
    0.75
    Activations Density 0.040%

    No Known Activations