© 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. 7-RES-JB
    11. 13568
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement

    oai_token-act-pair · gpt-3.5-turbo

    themes of mental health and emotional resilience

    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
    Basically
    -0.89
    Specifically
    -0.84
    umably
    -0.83
    Phase
    -0.82
    Additionally
    -0.80
     specifically
    -0.77
    Obviously
    -0.76
     involvement
    -0.72
    Interestingly
    -0.71
     commenters
    -0.71
    POSITIVE LOGITS
     thou
    1.07
     vain
    0.98
     thee
    0.96
     thy
    0.95
    morrow
    0.90
     mighty
    0.86
     glory
    0.86
     tremb
    0.85
     splend
    0.82
    arest
    0.82
    Activations Density 0.680%

    No Known Activations