© 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. 2-RES-JB
    11. 821
    Prev
    Next
    INDEX
    Explanations

    the gerund form of the verb 'track' (tracking)

    oai_token-act-pair · gpt-4-turbo

    instances of the word "tracking"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tracking" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahu
    -0.75
    adding
    -0.71
    sis
    -0.70
    Ann
    -0.69
    lvl
    -0.68
    ima
    -0.67
    si
    -0.67
    lihood
    -0.66
    forth
    -0.66
    urt
    -0.65
    POSITIVE LOGITS
     tracking
    0.94
     tracks
    0.90
     tracked
    0.90
     Tracks
    0.88
    eers
    0.87
     tabs
    0.84
     track
    0.81
     bracelet
    0.80
    ttes
    0.73
    itored
    0.73
    Activations Density 0.017%

    No Known Activations