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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 9-RES-JB
    6. 16926
    Prev
    Next
    INDEX
    Explanations

    phrases describing physical actions involving hands and arms

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts to create comparisons or describe actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosyncr
    -0.76
    Planet
    -0.66
    è£ħ
    -0.64
    Manufact
    -0.63
    quist
    -0.63
    Gender
    -0.62
    tty
    -0.59
    ãĤ¼
    -0.59
    Ess
    -0.58
    Intern
    -0.58
    POSITIVE LOGITS
    phy
    0.91
     they
    0.88
     dusk
    0.85
    piring
    0.84
    bestos
    0.81
     soon
    0.81
     follows
    0.80
     well
    0.80
     he
    0.80
    pired
    0.78
    Activations Density 0.122%

    No Known Activations