© 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. 1-RES-JB
    11. 930
    Prev
    Next
    INDEX
    Explanations

    the name "Dan" in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.70
     midterm
    -0.68
    */(
    -0.67
     predictive
    -0.66
     subsystem
    -0.66
     actionGroup
    -0.65
     synaptic
    -0.64
     depress
    -0.63
    tty
    -0.62
     behav
    -0.62
    POSITIVE LOGITS
    dan
    1.30
    ovic
    1.12
    forth
    1.12
    zinski
    1.06
    igans
    0.97
    ovich
    0.93
    olin
    0.91
    ahar
    0.90
    jen
    0.90
    han
    0.88
    Activations Density 0.008%

    No Known Activations