© 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. 11-RES-JB
    11. 23856
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific entities

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the phrase "Et" or variations of it in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪ¦
    -0.63
     DOE
    -0.58
    Origin
    -0.55
    anmar
    -0.55
     Earthquake
    -0.54
    against
    -0.54
    FUL
    -0.54
     indict
    -0.54
     widely
    -0.53
     [+
    -0.53
    POSITIVE LOGITS
    iquette
    1.57
    ihad
    1.27
    udes
    1.21
    ienne
    1.20
    ude
    1.09
    ween
    1.07
    iology
    1.03
    obic
    0.96
    ernal
    0.91
    ching
    0.89
    Activations Density 0.029%

    No Known Activations