INDEX

Explanations

negations or statements of falsity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 poffible

-0.70

 purpoſe

-0.66

oa̍t

-0.66

 leſs

-0.65

 ſche

-0.65

 reaſon

-0.65

 abſ

-0.65

toPromise

-0.65

 fhort

-0.65

 pleaſure

-0.65

POSITIVE LOGITS

 تضيفلها

0.66

0.65

RenderAtEndOf

0.57

–

0.55

‐

0.54

Дереккөздер

0.53

ніципа

0.51

ItemBackground

0.51

 saites

0.49

ագրություններ

0.49

Activations Density 0.331%

negations or statements of falsity

No Comments

No Known Activations