© 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. 6-RES-JB
    11. 3664
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and financial topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governance, policy, and various social rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irlf
    -0.74
    arya
    -0.68
    pora
    -0.67
    emet
    -0.66
    anke
    -0.65
    ONEY
    -0.65
    GMT
    -0.65
    BILITIES
    -0.65
    ideo
    -0.63
    lishes
    -0.63
    POSITIVE LOGITS
    tenance
    0.80
    osterone
    0.75
     hybrid
    0.71
    roying
    0.68
    quartered
    0.66
    ning
    0.63
     hybrids
    0.62
    ïve
    0.61
     syndrome
    0.60
    ergic
    0.59
    Activations Density 0.363%

    No Known Activations