Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24530
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or venues where events are taking place

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "at" followed by a time or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.84
    FTWARE
    -0.81
    Lens
    -0.75
    rider
    -0.69
    Russ
    -0.69
    REDACTED
    -0.68
    bender
    -0.67
    quel
    -0.66
    blade
    -0.65
    aceutical
    -0.65
    POSITIVE LOGITS
     least
    1.18
     halftime
    0.96
    onement
    0.84
     weekends
    0.83
    abase
    0.79
    yp
    0.79
    roph
    0.77
     cafes
    0.76
     airports
    0.76
     whim
    0.75
    Activations Density 0.183%

    No Known Activations