© 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. 7-RES-JB
    11. 4004
    Prev
    Next
    INDEX
    Explanations

    terms related to conversational skills or vocational education

    oai_token-act-pair · gpt-3.5-turbo

    words that pertain to different specialized or applied fields, often indicated by the suffix '-ational'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.86
     âĶľ
    -0.82
    Nap
    -0.73
    Veter
    -0.73
    cedented
    -0.73
    ãģ®éŃĶ
    -0.73
    lda
    -0.72
    UV
    -0.71
    IRD
    -0.68
    vier
    -0.68
    POSITIVE LOGITS
    ity
    1.16
    ities
    1.11
    ized
    1.07
    ization
    0.99
    izing
    0.95
    ists
    0.93
    isations
    0.92
    ité
    0.88
    ism
    0.87
    ist
    0.86
    Activations Density 0.128%

    No Known Activations