© 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. 4-RES-JB
    11. 2830
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases associated with negative perceptions or impacts

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

    No Comments

    Negative Logits
    conservancy
    -0.85
    adr
    -0.84
    DOM
    -0.83
    pread
    -0.83
    hower
    -0.82
    ITNESS
    -0.82
    akings
    -0.81
    rote
    -0.79
    igs
    -0.77
    allows
    -0.77
    POSITIVE LOGITS
     reinforcement
    1.09
     Negative
    0.93
     feedback
    0.89
     spiral
    0.87
     negative
    0.86
     impact
    0.85
     publicity
    0.85
     vib
    0.84
     gearing
    0.83
     stigma
    0.83
    Activations Density 0.014%

    No Known Activations