© 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. 17653
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "It"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "It is" or similar constructs indicating statements

    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
     convincing
    -0.58
     dissenting
    -0.54
     persuasion
    -0.54
     Monte
    -0.53
     2048
    -0.52
    ĺħ
    -0.52
     citing
    -0.52
     afar
    -0.52
     PUBLIC
    -0.50
     arguing
    -0.50
    POSITIVE LOGITS
    iner
    1.06
     sounds
    1.02
     Begins
    1.02
     ain
    1.00
    alia
    1.00
     seems
    0.99
    unes
    0.99
     wasn
    0.98
    amar
    0.96
    alian
    0.96
    Activations Density 0.151%

    No Known Activations