© 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. 0-RES-JB
    6. 4189
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "With" followed by a verb or adjective

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "With" followed by a high degree of descriptive content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iles
    -0.66
     people
    -0.61
     comm
    -0.61
     trivial
    -0.59
     biological
    -0.58
     lifes
    -0.57
     speakers
    -0.57
     incrim
    -0.56
    ologies
    -0.56
     identical
    -0.56
    POSITIVE LOGITS
     With
    2.83
    With
    2.12
     Without
    1.86
     Together
    1.56
     WITH
    1.55
     While
    1.54
     Through
    1.54
     Along
    1.54
     Having
    1.49
     Using
    1.47
    Activations Density 0.022%

    No Known Activations