© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20429
    Prev
    Next
    INDEX
    Explanations

    phrases related to change over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate associations with age and time

    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
    arc
    -0.81
    querque
    -0.76
    NN
    -0.74
    «ĺ
    -0.72
    uns
    -0.72
    ãĤ¤ãĥĪ
    -0.72
    oeuv
    -0.71
    Virgin
    -0.69
    anners
    -0.68
    apest
    -0.68
    POSITIVE LOGITS
     horizont
    0.81
     repetition
    0.80
     inflation
    0.74
     saturation
    0.71
     depreciation
    0.70
     therap
    0.70
     magnification
    0.69
     repet
    0.68
     realization
    0.66
     enlarg
    0.65
    Activations Density 0.384%

    No Known Activations