INDEX

Explanations

the word "except" and its contexts related to exclusions or limitations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ex

-0.55

 immun

-0.55

 still

-0.54

DataBind

-0.52

ance

-0.52

 Immun

-0.51

ex

-0.51

 MainAxisSize

-0.51

 AdapterView

-0.49

ieri

-0.49

POSITIVE LOGITS

")){

0.66

">:

0.64

latego

0.63

 chofe

0.63

Thing

0.62

ựng

0.62

 softened

0.61

 excepto

0.61

ďaka

0.61

writeFieldEnd

0.60

Activations Density 0.107%

the word "except" and its contexts related to exclusions or limitations

No Comments

No Known Activations