© 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. 4986
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cause-and-effect analysis and cost-benefit evaluations

    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
    yss
    -0.76
    ADRA
    -0.74
     largeDownload
    -0.72
     rooft
    -0.68
    sonian
    -0.68
     Hollow
    -0.67
    Ü
    -0.65
    bley
    -0.65
    tle
    -0.63
    swick
    -0.62
    POSITIVE LOGITS
    benefit
    0.88
     incurred
    0.84
    effect
    0.79
     escalation
    0.75
    xious
    0.74
    effective
    0.71
    terness
    0.71
     effectiveness
    0.69
    azard
    0.69
    management
    0.68
    Activations Density 0.218%

    No Known Activations