© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9997
    Prev
    Next
    INDEX
    Explanations

    numeric figures and measurements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and the presence of the word "and" in various 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
    èª
    -0.72
    SpaceEngineers
    -0.72
    cture
    -0.64
    endif
    -0.60
    cially
    -0.59
    dayName
    -0.59
    hee
    -0.59
    rather
    -0.58
    Anyway
    -0.58
    EMOTE
    -0.57
    POSITIVE LOGITS
     150
    1.23
     250
    1.18
     144
    1.18
     120
    1.17
     140
    1.17
     132
    1.17
     160
    1.16
     170
    1.15
     176
    1.14
     175
    1.14
    Activations Density 0.219%

    No Known Activations