INDEX

Explanations

patterns or elements indicative of scientific terminology and variables

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ement

-0.54

 Vere

-0.48

nent

-0.47

ame

-0.45

mani

-0.45

Ye

-0.45

TIS

-0.44

xis

-0.44

aren

-0.43

uket

-0.43

POSITIVE LOGITS

NameInMap

0.96

PW

0.94

MW

0.90

PW

0.89

AW

0.87

GW

0.85

LW

0.84

HW

0.81

BW

0.81

twimg

0.81

Activations Density 0.385%

patterns or elements indicative of scientific terminology and variables

No Comments

No Known Activations