INDEX

Explanations

elements related to form submissions or administrative actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

addContainerGap

-0.66

Sh

-0.48

抱

-0.48

 strconv

-0.48

 EdgeInsets

-0.47

int

-0.47

 Lett

-0.47

paru

-0.45

gü

-0.45

__':

-0.45

POSITIVE LOGITS

 propOrder

0.63

 FIELDS

0.63

 myſelf

0.62

 blanks

0.61

 AssemblyTitle

0.61

 boxes

0.60

 fields

0.60

 purpoſe

0.59

 scania

0.58

xase

0.58

Activations Density 0.152%

elements related to form submissions or administrative actions

No Comments

No Known Activations