© 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. 7-RES-JB
    11. 23709
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating positions or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating spatial or positional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cred
    -0.64
     assumes
    -0.63
    awaru
    -0.62
     alloc
    -0.61
     thereafter
    -0.60
     arising
    -0.59
    Attempts
    -0.58
    IRE
    -0.58
     subsequently
    -0.58
     allocations
    -0.58
    POSITIVE LOGITS
    acebook
    0.86
    itable
    0.84
    lined
    0.81
    omorphic
    0.80
    uba
    0.77
    ited
    0.77
    ped
    0.76
    fed
    0.76
    active
    0.76
    pport
    0.75
    Activations Density 0.231%

    No Known Activations