© 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. 8-RES-JB
    11. 18754
    Prev
    Next
    INDEX
    Explanations

    references to the "Free Press."

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Free," indicating a focus on content related to the Free Press

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therap
    -0.88
    ENTS
    -0.76
    iop
    -0.72
    è¦ļéĨĴ
    -0.72
     deceive
    -0.71
    uality
    -0.71
    ional
    -0.71
    iot
    -0.68
    ENT
    -0.67
     positively
    -0.66
    POSITIVE LOGITS
    zing
    1.05
    bies
    1.01
    zes
    1.01
    bie
    0.92
    zers
    0.89
    zer
    0.85
    edom
    0.83
    BSD
    0.79
    boot
    0.78
    gans
    0.77
    Activations Density 0.025%

    No Known Activations