© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 2631
    Prev
    Next
    INDEX
    Explanations

    years mentioned as dates

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific numeric codes or identifiers, particularly in relation to films or academic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bots
    -0.66
     asses
    -0.63
    EStream
    -0.61
     classified
    -0.60
     jugg
    -0.60
     pent
    -0.59
     backlog
    -0.59
     polyg
    -0.58
     plateau
    -0.58
    EStreamFrame
    -0.58
    POSITIVE LOGITS
    62
    1.34
    61
    1.33
    54
    1.26
    53
    1.25
    56
    1.23
    52
    1.21
    58
    1.20
    57
    1.20
    49
    1.19
    51
    1.18
    Activations Density 0.019%

    No Known Activations