© 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. 24439
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format (e.g. Month Day, Year)

    oai_token-act-pair · gpt-3.5-turbo

    date 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
     glim
    -0.60
    venge
    -0.55
     mustard
    -0.54
    anca
    -0.54
     impe
    -0.54
    iliated
    -0.53
    hyde
    -0.53
     vast
    -0.53
     transf
    -0.52
    atem
    -0.52
    POSITIVE LOGITS
     27
    1.22
     29
    1.20
     28
    1.18
     26
    1.15
     31
    1.15
     23
    1.13
     22
    1.11
     2018
    1.11
     21
    1.10
     08
    1.09
    Activations Density 0.091%

    No Known Activations