© 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. 1-RES-JB
    11. 3103
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to news articles or publications

    oai_token-act-pair · gpt-3.5-turbo

    the abbreviation "PH" and its variations, indicating a focus on specific entities or terms with that acronym

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.84
    ãĥł
    -0.84
    ãĥĥ
    -0.83
     bloc
    -0.76
    hof
    -0.75
    eer
    -0.75
    ãĤ¤ãĥĪ
    -0.74
    ggles
    -0.74
    ãĥĭ
    -0.70
     Volks
    -0.70
    POSITIVE LOGITS
    PH
    1.27
    OTO
    1.15
    OTOS
    1.03
    ysics
    1.01
    ysis
    0.98
    anthrop
    0.95
    ASE
    0.94
    YS
    0.94
    ippi
    0.91
    tml
    0.89
    Activations Density 0.004%

    No Known Activations