© 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. 8-RES-JB
    11. 7624
    Prev
    Next
    INDEX
    Explanations

    phrases describing different aspects or variations of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the concept of "one" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.68
    cases
    -0.67
    ooks
    -0.67
    ories
    -0.65
    }:
    -0.63
    rollers
    -0.60
    ourn
    -0.58
    urations
    -0.57
     actionGroup
    -0.57
     è£ı
    -0.56
    POSITIVE LOGITS
     hundred
    0.83
     embodiment
    0.75
    elf
    0.74
     Hundred
    0.72
    cknowled
    0.71
    Shot
    0.70
     sided
    0.70
     thousand
    0.70
    idas
    0.68
     Thousand
    0.66
    Activations Density 0.069%

    No Known Activations