© 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. 20068
    Prev
    Next
    INDEX
    Explanations

    terms related to space exploration and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to space and related scientific concepts or institutions

    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
    rahim
    -0.73
     Zac
    -0.72
     Helpful
    -0.66
     Tuls
    -0.65
    aye
    -0.61
     Dill
    -0.60
     Baird
    -0.60
     recollection
    -0.60
     TCU
    -0.59
     PW
    -0.59
    POSITIVE LOGITS
    ioxide
    1.22
    idon
    0.87
    obos
    0.87
     continuum
    0.78
    estial
    0.77
    agos
    0.73
     sciences
    0.71
    ternity
    0.70
    OVA
    0.70
    imeter
    0.69
    Activations Density 0.232%

    No Known Activations