© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    specific phrases instructing to obtain information or subscribe for updates

    oai_token-act-pair · gpt-3.5-turbo

    commands or calls to action

    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
    ISC
    -0.60
     makeshift
    -0.59
     sealing
    -0.59
     archae
    -0.59
     devout
    -0.57
    mouth
    -0.57
    anity
    -0.56
     defe
    -0.56
     reson
    -0.56
     welcoming
    -0.56
    POSITIVE LOGITS
    TING
    1.09
    aways
    0.88
     rid
    0.85
    away
    0.82
    gets
    0.80
    Get
    0.79
     Started
    0.79
    zl
    0.78
    gotten
    0.75
     Tickets
    0.74
    Activations Density 0.019%

    No Known Activations