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. 17999
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, particularly "Robbie"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those related to sports or specific events

    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
    igators
    -0.81
    nesia
    -0.78
    ngth
    -0.72
    ainment
    -0.72
    OA
    -0.70
    gor
    -0.70
    ure
    -0.68
    aternity
    -0.68
    igator
    -0.67
    ebin
    -0.67
    POSITIVE LOGITS
     McF
    0.91
     Robbie
    0.82
    eatures
    0.76
     McKenzie
    0.72
    ggles
    0.72
     Keane
    0.67
    eco
    0.67
     Lowe
    0.66
     Thomson
    0.66
    elsius
    0.65
    Activations Density 0.024%

    No Known Activations