© 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. 1-RES-JB
    11. 5420
    Prev
    Next
    INDEX
    Explanations

    proper nouns in a specific format with capitalized letters interspersed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "As" and variations of terms or labels associated with a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.71
     BaseType
    -0.68
     unfocusedRange
    -0.64
    ãĤ¨ãĥ«
    -0.64
     streng
    -0.63
    ¥ŀ
    -0.63
     Emer
    -0.61
     tremend
    -0.61
    ãĥĪ
    -0.59
     circ
    -0.59
    POSITIVE LOGITS
    QL
    0.95
    emale
    0.89
    ocrine
    0.86
    HS
    0.84
    IX
    0.84
    ACE
    0.83
    idia
    0.83
    ILL
    0.80
    xi
    0.79
    atics
    0.77
    Activations Density 0.442%

    No Known Activations