© 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. 9-RES-JB
    11. 6978
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by modal verbs indicating possibilities or abilities

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating agency and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unavoidable
    -0.62
     Citation
    -0.61
     reinforcement
    -0.61
     Joint
    -0.61
     srfAttach
    -0.61
     contrasting
    -0.60
     contrary
    -0.60
     Key
    -0.60
     Eleven
    -0.60
     gratification
    -0.59
    POSITIVE LOGITS
    'll
    1.31
    're
    1.21
    've
    1.07
    eding
    1.05
    irs
    1.05
    cair
    0.96
    'd
    0.96
    ather
    0.95
    'm
    0.92
    iltr
    0.88
    Activations Density 0.291%

    No Known Activations