© 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. 7-RES-JB
    11. 15663
    Prev
    Next
    INDEX
    Explanations

    numbers relating to time durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to numerical quantities and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dearly
    -0.74
    dale
    -0.72
    stained
    -0.67
    bra
    -0.67
    liest
    -0.66
    alin
    -0.65
    rower
    -0.64
    abee
    -0.64
    geon
    -0.63
     Blues
    -0.60
    POSITIVE LOGITS
     dozen
    0.89
     thous
    0.84
    dozen
    0.83
    %"
    0.81
     percent
    0.77
    OTAL
    0.77
     thirds
    0.76
     miles
    0.66
    300
    0.64
    addons
    0.64
    Activations Density 0.160%

    No Known Activations