© 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. 10-RES-JB
    11. 2969
    Prev
    Next
    INDEX
    Explanations

    dates mentioned within sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to time, location, and organizational entities

    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
     Whilst
    -1.12
     whilst
    -1.03
     realise
    -0.98
    Firstly
    -0.97
     recognise
    -0.92
     apologise
    -0.85
     util
    -0.84
    £
    -0.84
    ãĥİ
    -0.83
    colour
    -0.82
    POSITIVE LOGITS
     lawmakers
    1.14
     attorneys
    1.09
     Gov
    1.05
     officials
    1.03
     investigators
    1.03
     federal
    1.02
     Reps
    1.00
     executives
    0.99
     POLITICO
    0.98
     longtime
    0.97
    Activations Density 0.617%

    No Known Activations