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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 1227
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing or influencing change or advancement

    oai_token-act-pair · gpt-3.5-turbo

    verbs associated with influence or motivation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -1.00
    çĦ
    -0.84
    ereo
    -0.76
    alg
    -0.70
    namese
    -0.69
    roma
    -0.68
    yip
    -0.67
    thren
    -0.66
    aido
    -0.66
    alon
    -0.65
    POSITIVE LOGITS
     wedge
    0.87
     driving
    0.80
     away
    0.80
    ousel
    0.71
    oused
    0.69
     driven
    0.68
    train
    0.66
     home
    0.66
    driving
    0.65
    wheel
    0.65
    Activations Density 0.030%

    No Known Activations