© 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. 4-RES-JB
    11. 8584
    Prev
    Next
    INDEX
    Explanations

    specific numeric values, particularly those related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those around the figure 150

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

    No Comments

    Negative Logits
    gotten
    -0.84
    ucle
    -0.81
    omial
    -0.81
    phrine
    -0.80
    actic
    -0.76
    gone
    -0.75
    ufact
    -0.74
    puter
    -0.73
    odes
    -0.72
     Laden
    -0.69
    POSITIVE LOGITS
    Hz
    0.81
    rpm
    0.75
    hz
    0.75
    ansas
    0.74
    escription
    0.73
    rets
    0.73
    wcsstore
    0.72
    IRED
    0.69
    JV
    0.68
    ivably
    0.67
    Activations Density 0.016%

    No Known Activations