© 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. 23463
    Prev
    Next
    INDEX
    Explanations

    sentences indicating that something is easily done or perceived

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating simplicity or ease

    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
    raints
    -0.77
    eters
    -0.76
    hips
    -0.71
    grave
    -0.70
    emp
    -0.65
    reen
    -0.65
    borg
    -0.64
    rongh
    -0.64
    inals
    -0.63
    bane
    -0.61
    POSITIVE LOGITS
    Jet
    1.00
     prey
    0.88
    coded
    0.80
    going
    0.79
     enough
    0.74
    pmwiki
    0.67
    wired
    0.66
    Deal
    0.66
    answer
    0.64
     easy
    0.63
    Activations Density 0.044%

    No Known Activations