© 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. 3-RES-JB
    11. 22700
    Prev
    Next
    INDEX
    Explanations

    phrases related to scaffolding or support structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structural or organizational frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftime
    -0.80
    orsche
    -0.76
    atile
    -0.75
    avy
    -0.73
    iss
    -0.72
    ophile
    -0.71
    ember
    -0.70
    irection
    -0.68
    ECD
    -0.68
    encers
    -0.68
    POSITIVE LOGITS
    framework
    0.89
     Pengu
    0.82
    inez
    0.79
    asu
    0.75
     Garfield
    0.73
    Interstitial
    0.73
     Goodman
    0.72
    ilan
    0.71
     actionGroup
    0.70
     Peb
    0.70
    Activations Density 0.020%

    No Known Activations