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. 22513
    Prev
    Next
    INDEX
    Explanations

    the concept of determination or desire to achieve something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "will" in various contexts related to intention or authority

    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
    eatures
    -0.71
    Aren
    -0.70
     Aren
    -0.68
    aughed
    -0.65
    ¥µ
    -0.65
     Topic
    -0.65
    orget
    -0.64
    eatured
    -0.63
     certific
    -0.62
     Sadd
    -0.61
    POSITIVE LOGITS
    fulness
    1.19
    power
    0.99
    FUL
    0.92
    ful
    0.89
    lessness
    0.88
    sburg
    0.86
    iness
    0.84
    iest
    0.83
    full
    0.82
    iam
    0.81
    Activations Density 0.041%

    No Known Activations