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. 19492
    Prev
    Next
    INDEX
    Explanations

    words related to professions or titles

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to various roles and positions in organizations or institutions

    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
    vironment
    -0.78
    schild
    -0.77
    ourning
    -0.74
    lyak
    -0.71
    imeo
    -0.70
    hovah
    -0.68
    ternity
    -0.68
    uden
    -0.66
    eas
    -0.65
    olithic
    -0.65
    POSITIVE LOGITS
    SHIP
    0.77
     thereof
    0.77
    ially
    0.76
    ship
    0.75
    itative
    0.73
    ial
    0.71
    ãĥĨãĤ£
    0.69
     extraord
    0.69
    itatively
    0.68
    Factor
    0.66
    Activations Density 0.117%

    No Known Activations