© 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. 4-RES-JB
    11. 12609
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express various activities or factors related to participation and availability

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

    No Comments

    Negative Logits
    ItemTracker
    -0.70
     Ily
    -0.65
    po
    -0.64
     IG
    -0.63
    bol
    -0.61
     Buk
    -0.60
     Beg
    -0.57
    ographer
    -0.56
     PAN
    -0.55
    Profile
    -0.55
    POSITIVE LOGITS
     respectively
    1.65
     alike
    1.47
     whichever
    0.98
    depending
    0.81
     interchange
    0.75
     thereof
    0.73
    asions
    0.70
     eras
    0.68
     respective
    0.68
    enei
    0.67
    Activations Density 1.332%

    No Known Activations