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. 13657
    Prev
    Next
    INDEX
    Explanations

    references to physical suffering and deprivation

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or identifiers related to addresses and statistics

    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
    querque
    -0.75
     exha
    -0.70
     reluct
    -0.67
     tremend
    -0.66
    anooga
    -0.66
     explan
    -0.63
     arming
    -0.62
    lying
    -0.62
     thous
    -0.61
    ibaba
    -0.61
    POSITIVE LOGITS
     MHz
    0.84
    458
    0.82
     ILCS
    0.81
    806
    0.81
    651
    0.80
    953
    0.79
    MHz
    0.79
    bps
    0.79
    994
    0.77
    884
    0.77
    Activations Density 0.081%

    No Known Activations