INDEX

Explanations

discussion of results or output in a document

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

"Result" or "Results"

np_acts-logits-general · gemini-2.0-flash

result of

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ialmente

-0.61

rinfo

-0.52

اطر

-0.51

Rohy

-0.50

 baile

-0.50

fice

-0.49

 rischi

-0.49

ionage

-0.48

viously

-0.48

 Teng

-0.48

POSITIVE LOGITS

स्व

0.77

물

0.69

Quo

0.67

 therefrom

0.64

mphony

0.63

 propOrder

0.63

 Infórmanos

0.62

RCS

0.61

 Roost

0.61

ibatis

0.59

Activations Density 0.235%

discussion of results or output in a document

"Result" or "Results"

result of

No Comments

No Known Activations