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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1273
    Prev
    Next
    INDEX
    Explanations

    words related to hindrance or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating negative impacts or hindrances caused by external 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
    esse
    -0.86
    uum
    -0.76
     uncond
    -0.74
    estamp
    -0.72
    umin
    -0.71
    ="#
    -0.71
    okes
    -0.70
    oker
    -0.70
    aves
    -0.68
    hal
    -0.68
    POSITIVE LOGITS
     bureaucratic
    0.85
     bureaucracy
    0.85
     accusations
    0.82
     scandals
    0.81
     inexper
    0.81
     shortages
    0.79
     setbacks
    0.79
     incompetence
    0.78
     Typhoon
    0.78
     successive
    0.78
    Activations Density 0.245%

    No Known Activations