© 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. 6-RES-JB
    11. 15295
    Prev
    Next
    INDEX
    Explanations

    adjectives or past participles followed by a possessive pronoun

    oai_token-act-pair · gpt-3.5-turbo

    references to assessments and evaluations related to ownership and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gart
    -0.68
    osate
    -0.67
     replaced
    -0.66
    âĢİ
    -0.66
     accompanied
    -0.66
    apters
    -0.65
    interrupted
    -0.64
    hari
    -0.63
    emonium
    -0.62
     Carmen
    -0.62
    POSITIVE LOGITS
     manner
    0.78
     outset
    0.73
     vein
    0.73
     slightest
    0.73
     uptake
    0.72
     direction
    0.71
     circumstances
    0.70
     caliber
    0.69
     purposes
    0.66
     seriousness
    0.66
    Activations Density 0.533%

    No Known Activations