© 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. 2-RES-JB
    11. 722
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sob" or words starting with "sob"

    oai_token-act-pair · gpt-4-turbo

    mentions of sobriety-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to sobriety or related emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.98
    geist
    -0.86
    netflix
    -0.83
    ãĤ¼ãĤ¦ãĤ¹
    -0.81
    æ©Ł
    -0.79
    tenance
    -0.77
    /+
    -0.74
    âĻ¦
    -0.73
    ãĥĪ
    -0.73
    ãĥ¤
    -0.72
    POSITIVE LOGITS
     sob
    1.14
    bing
    1.09
    ri
    0.96
    ilitating
    0.85
    riet
    0.84
    bed
    0.82
    bers
    0.81
    rolet
    0.81
    rine
    0.79
    ral
    0.78
    Activations Density 0.007%

    No Known Activations