© 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. 11-RES-JB
    11. 24107
    Prev
    Next
    INDEX
    Explanations

    advertisements

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisement or marketing references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiss
    -0.66
     territ
    -0.62
     wiser
    -0.62
     subdiv
    -0.61
     tremend
    -0.60
     pupils
    -0.60
     +/-
    -0.59
     newcom
    -0.59
     gaze
    -0.57
     civilisation
    -0.57
    POSITIVE LOGITS
    ADVERTISEMENT
    0.88
    ILY
    0.85
    GOP
    0.74
    \",
    0.74
    oving
    0.72
    \":
    0.71
    neau
    0.71
    both
    0.70
    Morning
    0.68
     âĢķ
    0.68
    Activations Density 0.120%

    No Known Activations