INDEX

Explanations

occurrences of the character "e"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

-0.72

Tembelea

-0.62

TagHelpers

-0.58

nt

-0.57

Zum

-0.56

GTCX

-0.56

st

-0.55

quations

-0.55

dios

-0.55

POSITIVE LOGITS

 GenerationType

0.51

 NgModule

0.51

 TextAppearance

0.49

 démocr

0.48

an

0.48

 resourceCulture

0.44

AutoField

0.44

ir

0.44

ej

0.43

 financières

0.42

Activations Density 0.215%

occurrences of the character "e"

No Comments

No Known Activations