Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the addition or inclusion of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions that involve the words "in" or "a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =]
    -0.72
    MQ
    -0.68
    Ring
    -0.68
    STER
    -0.66
    orius
    -0.66
     FIGHT
    -0.61
    MODE
    -0.60
     Registry
    -0.59
    catentry
    -0.59
    ulet
    -0.59
    POSITIVE LOGITS
     reinforcements
    1.01
    animate
    0.98
    ordinate
    0.86
    effic
    0.85
    clusions
    0.83
     excess
    0.83
     extra
    0.79
     lieu
    0.76
    tics
    0.76
     some
    0.76
    Activations Density 0.045%

    No Known Activations