© 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. 6-RES-JB
    11. 19720
    Prev
    Next
    INDEX
    Explanations

    locations with associated dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" related to various locations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.67
    arth
    -0.66
    REL
    -0.65
    hement
    -0.64
     concedes
    -0.62
    anon
    -0.62
    henko
    -0.61
    lando
    -0.60
     assures
    -0.60
    killed
    -0.59
    POSITIVE LOGITS
     winter
    0.72
    ember
    0.66
     September
    0.66
     tourist
    0.65
    soDeliveryDate
    0.64
     Week
    0.64
    ignt
    0.63
     behalf
    0.62
     1893
    0.62
    FINE
    0.62
    Activations Density 0.289%

    No Known Activations