© 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. 11-RES-JB
    11. 24127
    Prev
    Next
    INDEX
    Explanations

    people and entities being blamed for actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of blame directed toward individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     largeDownload
    -0.57
    ãĤ¼ãĤ¦ãĤ¹
    -0.53
    igate
    -0.51
     Taken
    -0.51
    ãĥĪ
    -0.50
    requires
    -0.50
    unda
    -0.50
    ire
    -0.50
    pires
    -0.50
     practicable
    -0.49
    POSITIVE LOGITS
     for
    1.30
    for
    1.14
     FOR
    0.89
    For
    0.88
    FOR
    0.84
     For
    0.82
    ÄŁ
    0.70
    é¾į
    0.67
     unres
    0.63
     harshly
    0.62
    Activations Density 0.722%

    No Known Activations