INDEX

Explanations

occurrences of the term "first" and related ordinal indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 externi

-0.61

Билгалдахарш

-0.59

parsedMessage

-0.59

مصادر

-0.57

AndEndTag

-0.57

ruitment

-0.57

organizzazione

-0.56

 lenker

-0.54

\{\\

-0.54

Unmarshaller

-0.51

POSITIVE LOGITS

 rate

0.60

 Amendment

0.60

apunov

0.58

 string

0.55

HAND

0.54

string

0.54

 annual

0.53

:"-

0.53

tisgarh

0.53

hand

0.52

Activations Density 0.156%

occurrences of the term "first" and related ordinal indicators

No Comments

No Known Activations