© 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. 10-RES-JB
    11. 20212
    Prev
    Next
    INDEX
    Explanations

    word pairs that contrast between "objective" and "subjective."

    oai_token-act-pair · gpt-3.5-turbo

    distinctions between objective and subjective terms or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letters
    -0.92
    birds
    -0.87
    olini
    -0.85
     Tycoon
    -0.82
    eland
    -0.81
    bird
    -0.76
    Lago
    -0.76
    olina
    -0.76
    stall
    -0.75
    ners
    -0.75
    POSITIVE LOGITS
     evaluation
    1.08
     appraisal
    1.06
     observer
    1.05
     criteria
    1.03
     measurement
    1.02
     evaluations
    1.00
     pronoun
    0.97
     assessment
    0.97
     judgement
    0.96
     analy
    0.95
    Activations Density 0.057%

    No Known Activations