© 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. 8-RES-JB
    11. 23398
    Prev
    Next
    INDEX
    Explanations

    instances of the word "more" used in the context of discussing increasing quantities or frequency of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "more" in various contexts indicating an increase or escalation

    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
    ĺħ
    -0.79
    ovie
    -0.78
    xtap
    -0.71
    ħĭ
    -0.68
    ramid
    -0.66
    ube
    -0.64
    atan
    -0.64
    uyomi
    -0.63
    bat
    -0.63
    minus
    -0.63
    POSITIVE LOGITS
     than
    1.14
     importantly
    1.10
     stringent
    0.93
     sophisticated
    0.84
     emphasis
    0.83
     frequent
    0.83
     affluent
    0.79
     broadly
    0.79
     rigorous
    0.79
     worrisome
    0.77
    Activations Density 0.110%

    No Known Activations