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

    Neuronpedia

    APICircuit 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. 9-RES-JB
    6. 14915
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format, likely in the context of historical events or films

    oai_token-act-pair · gpt-3.5-turbo

    numerical references, particularly dates

    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
    EStreamFrame
    -0.89
     classified
    -0.76
     asses
    -0.70
     Bots
    -0.67
     brackets
    -0.67
     Bundy
    -0.66
     backlog
    -0.60
     polyg
    -0.60
     athlet
    -0.59
     servers
    -0.59
    POSITIVE LOGITS
    61
    1.24
    62
    1.20
    56
    1.05
    54
    1.05
    53
    1.02
    52
    1.01
    58
    1.00
    57
    1.00
    âĸĪâĸĪ
    1.00
    08
    0.99
    Activations Density 0.030%

    No Known Activations