© 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. 6244
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or contexts signified by "here" and "there"

    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
     sshd
    -0.67
     Detection
    -0.65
     Susp
    -0.63
    susp
    -0.62
    76561
    -0.60
     Illum
    -0.59
     Donation
    -0.57
     collisions
    -0.57
     psychiatry
    -0.56
     detection
    -0.55
    POSITIVE LOGITS
    iah
    0.73
    女
    0.72
     Chile
    0.71
    abad
    0.70
     elsewhere
    0.69
    ħĭ
    0.68
    anchester
    0.66
    ignty
    0.65
    çīĪ
    0.65
    NOW
    0.64
    Activations Density 0.095%

    No Known Activations