© 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. 2331
    Prev
    Next
    INDEX
    Explanations

    phrases containing the abbreviation "Ph"

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "Ph" indicating a focus on philosophical topics or discussions

    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
    éĹĺ
    -0.94
     fit
    -0.80
    PUT
    -0.73
     fitting
    -0.72
    âĸ¬âĸ¬
    -0.71
     stroke
    -0.71
    ãģ®éŃĶ
    -0.69
    HCR
    -0.69
    TING
    -0.65
     shortened
    -0.65
    POSITIVE LOGITS
    osph
    1.46
    antom
    1.35
    ysics
    1.24
    rase
    1.21
    armac
    1.20
    ases
    1.20
    asing
    1.18
    ilipp
    1.17
    obia
    1.17
    obos
    1.13
    Activations Density 0.021%

    No Known Activations