© 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. 7205
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking a stand or stance on a particular issue or belief

    oai_token-act-pair · gpt-3.5-turbo
    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
    lys
    -0.76
    REDACTED
    -0.73
    quartered
    -0.73
    Pen
    -0.71
    soon
    -0.69
    JJ
    -0.68
    pour
    -0.68
    unn
    -0.66
    native
    -0.65
    ucl
    -0.64
    POSITIVE LOGITS
     ideals
    0.98
     equality
    0.85
     Yourself
    0.84
     principles
    0.83
     freedoms
    0.83
     Integrity
    0.82
     integrity
    0.82
     reelection
    0.81
     liberty
    0.81
     something
    0.80
    Activations Density 0.063%

    No Known Activations