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. 7-RES-JB
    6. 15631
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning the concept of impossibility or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or impossibility without certain elements or factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.84
    mon
    -0.82
    ãĥī
    -0.81
    ery
    -0.79
    visor
    -0.75
    ãĥĺ
    -0.73
    rolled
    -0.71
    iph
    -0.69
    quer
    -0.68
    late
    -0.67
    POSITIVE LOGITS
     knowing
    0.93
     recourse
    0.88
     regard
    0.87
     sacrificing
    0.86
     risking
    0.83
     compromising
    0.83
     mentioning
    0.81
     respect
    0.76
     encountering
    0.75
     respecting
    0.70
    Activations Density 0.029%

    No Known Activations