INDEX

Explanations

text segments that contain formatting or appear to be part of a structured document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

oredCriteria

-0.53

ToBounds

-0.46

ymce

-0.43



-0.42

ByExample

-0.41

 físicos

-0.40

 femeninos

-0.40

 længere

-0.39

TextWatcher

-0.39

 smtplib

-0.38

POSITIVE LOGITS

\{\\

0.59

RenderAtEndOf

0.59

 defaultstate

0.57

findpost

0.55

ISupport

0.50

IZONT

0.49

Pose

0.47

 banner

0.46

DockStyle

0.46

Fung

0.45

Activations Density 0.001%

text segments that contain formatting or appear to be part of a structured document

No Comments

No Known Activations