© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 14845
    Prev
    Next
    INDEX
    Explanations

    phrases containing the concept of "opening doors" or providing access to something

    oai_token-act-pair · gpt-3.5-turbo

    prepositions that indicate relationships or connections between subjects

    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
    Äĩ
    -0.82
    uggest
    -0.81
    rencies
    -0.79
    akeru
    -0.77
    zbollah
    -0.76
    isi
    -0.74
    ibo
    -0.74
    oday
    -0.74
    oup
    -0.73
    tumblr
    -0.73
    POSITIVE LOGITS
     unsuspecting
    0.71
    ifice
    0.70
     desks
    0.70
     flats
    0.69
     Settlement
    0.66
     darkened
    0.65
     confines
    0.64
     floors
    0.63
     myster
    0.63
     Devils
    0.62
    Activations Density 0.374%

    No Known Activations