© 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. 3-RES-JB
    6. 11393
    Prev
    Next
    INDEX
    Explanations

    phrases stating a fact or indicating certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the state or condition of a subject

    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
    itches
    -0.70
    bies
    -0.68
     Apart
    -0.66
     Peoples
    -0.65
    rarily
    -0.64
     Hitch
    -0.64
    kson
    -0.62
    itching
    -0.62
    mons
    -0.62
    ricks
    -0.61
    POSITIVE LOGITS
    nt
    0.99
     supposed
    0.85
     meant
    0.83
     actually
    0.78
     immune
    0.74
    omorphic
    0.73
     unlikely
    0.73
     NOT
    0.71
     probably
    0.71
     not
    0.71
    Activations Density 0.498%

    No Known Activations