© 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. 3305
    Prev
    Next
    INDEX
    Explanations

    names containing the syllable "ams"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific places or events

    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
    Charge
    -0.67
     hazard
    -0.66
     seniors
    -0.63
     escalation
    -0.61
     partisans
    -0.60
     fluid
    -0.59
     draw
    -0.59
     Heb
    -0.59
     danger
    -0.59
    Footnote
    -0.59
    POSITIVE LOGITS
    ams
    1.34
    ãĤ¤ãĥĪ
    1.02
    arah
    1.00
    ateur
    0.99
    sterdam
    0.99
    heet
    0.95
    alam
    0.93
    amed
    0.92
    ueller
    0.90
    chool
    0.89
    Activations Density 0.003%

    No Known Activations