© 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. 17320
    Prev
    Next
    INDEX
    Explanations

    instances of words related to providing assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    terms related to relief, particularly in contexts addressing assistance or alleviation

    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
    eton
    -0.82
     Bulg
    -0.73
    tein
    -0.70
    asus
    -0.69
    lished
    -0.68
    0000000000000000
    -0.68
     Wilde
    -0.67
    ozy
    -0.66
    ova
    -0.66
    atu
    -0.66
    POSITIVE LOGITS
     relief
    0.96
    ilitation
    0.91
     pitcher
    0.85
     valve
    0.84
     pitchers
    0.79
     packages
    0.79
     efforts
    0.79
     package
    0.76
    s
    0.76
     valves
    0.75
    Activations Density 0.039%

    No Known Activations