© 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. 0-RES-JB
    11. 23173
    Prev
    Next
    INDEX
    Explanations

    phrases related to electrical wiring or connection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to electrical connections and wiring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    paralle
    -0.67
     endorsements
    -0.65
    Cast
    -0.64
    vec
    -0.64
    yu
    -0.63
     Crit
    -0.62
     bombard
    -0.61
    actionDate
    -0.61
     programme
    -0.61
     Sor
    -0.61
    POSITIVE LOGITS
     wired
    2.65
    wired
    1.78
     disposed
    1.73
     flush
    1.52
     dispos
    1.44
     laundering
    1.38
     flushed
    1.25
     wiring
    1.24
     poker
    1.19
     dispose
    1.12
    Activations Density 0.067%

    No Known Activations