© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    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
    heit
    -0.71
    ontent
    -0.70
    berman
    -0.69
    ecided
    -0.67
    lly
    -0.66
    ratulations
    -0.64
    erva
    -0.64
    veland
    -0.62
    scape
    -0.62
    ional
    -0.62
    POSITIVE LOGITS
     outset
    1.27
     same
    1.22
     behest
    1.10
     latter
    0.99
     slightest
    0.99
     periphery
    0.95
     moment
    0.95
     forefront
    0.93
     earliest
    0.90
     end
    0.89
    Activations Density 0.204%

    No Known Activations