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. 17155
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Kind" often associated with different contexts and content

    oai_token-act-pair · gpt-3.5-turbo

    references to "Kindles" and related products or features

    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
    è¦ļéĨĴ
    -0.88
    Downloadha
    -0.80
    apons
    -0.77
    VEL
    -0.75
    IVER
    -0.73
    pez
    -0.72
    berus
    -0.71
    UNCH
    -0.70
    ZI
    -0.70
    ptions
    -0.67
    POSITIVE LOGITS
    ness
    1.08
    hearted
    0.96
    ening
    0.94
    ened
    0.91
    erman
    0.91
    liness
    0.88
    red
    0.88
    leness
    0.88
    ling
    0.84
    elf
    0.82
    Activations Density 0.022%

    No Known Activations