© 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. 2323
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or passage through physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific phrases indicating titles or significant concepts related to a 'gift shop'

    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
    tle
    -0.76
    CVE
    -0.73
    onga
    -0.66
    oka
    -0.65
    Percent
    -0.65
    pi
    -0.63
    iru
    -0.63
    zu
    -0.62
     suppose
    -0.61
    IAN
    -0.61
    POSITIVE LOGITS
     veins
    1.11
     motions
    1.09
     entirety
    1.01
     prism
    1.00
     backdoor
    0.98
     ranks
    0.98
     haze
    0.94
     process
    0.94
     midst
    0.93
     corridors
    0.93
    Activations Density 0.148%

    No Known Activations