INDEX

Explanations

specific identifiers or labels in data, particularly in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setVerticalGroup

-0.64

ględ

-0.52

angliski

-0.51

Spoljašnje

-0.51

oa̍t

-0.50

tetlen

-0.49

webElement

-0.47

 rimu

-0.46

rtz

-0.46

 mAdapter

-0.46

POSITIVE LOGITS

afficheront

0.80

 NSCoder

0.79

 оригіналу

0.71

Hochspringen

0.68

ⓘ

0.68

BeginContext

0.68

AutoScaleMode

0.67

ScopeManager

0.66

Skocz

0.66

مصادر

0.65

Activations Density 0.202%

specific identifiers or labels in data, particularly in a structured format

No Comments

No Known Activations