© 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. 1-RES-JB
    11. 16361
    Prev
    Next
    INDEX
    Explanations

    references to specific names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names associated with notable public figures or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioch
    -0.68
    rax
    -0.67
     fielded
    -0.66
    unct
    -0.65
     underest
    -0.62
    ed
    -0.62
    sterdam
    -0.62
    roman
    -0.61
     underestimated
    -0.61
    rifice
    -0.60
    POSITIVE LOGITS
     Dunham
    1.19
     Gw
    1.19
     Lena
    1.10
     Scotia
    0.86
    estone
    0.83
    istor
    0.77
     Chu
    0.75
     Tina
    0.74
     Juice
    0.73
     Turner
    0.72
    Activations Density 0.006%

    No Known Activations