© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1629
    Prev
    Next
    INDEX
    Explanations

    positive and negative sentiments towards various topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases reflecting attitudes and evaluations, particularly about kindness and negativity

    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
    UNCH
    -0.78
    ĸļ
    -0.73
     impossibility
    -0.73
    utter
    -0.70
    igsaw
    -0.68
    rame
    -0.66
    ulo
    -0.62
    alsa
    -0.60
    igs
    -0.60
    rossover
    -0.60
    POSITIVE LOGITS
     toward
    1.16
     towards
    1.12
     Towards
    0.86
     disposed
    0.85
     relations
    0.85
    itism
    0.82
     attitude
    0.77
     gays
    0.73
    Semitic
    0.71
     demeanor
    0.70
    Activations Density 0.440%

    No Known Activations