INDEX

Explanations

specific numerical references or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Transmission

-0.44

[*]

-0.43

 Transfer

-0.43

 transmission

-0.43

Transfer

-0.42

وص

-0.41

 transmisión

-0.41

 hydrolysis

-0.41

 तक

-0.40

vors

-0.40

POSITIVE LOGITS

InstanceState

0.79

NgModule

0.79

 NgModule

0.72

 '\\;'

0.71

دانشنامهٔ

0.71

RenderAtEndOf

0.70

awtextra

0.69

aarrggbb

0.68

 חיצוניים

0.68

AndEndTag

0.68

Activations Density 0.370%

specific numerical references or data points

No Comments

No Known Activations