INDEX

Explanations

elements relating to barriers and overcoming obstacles in various contexts

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

addCriterion

-0.82

 AssemblyCulture

-0.82

ImageContext

-0.81

ViewFeatures

-0.80

Vidite

-0.75

 Roskov

-0.66

 onPostExecute

-0.65

DebuggerNonUser

-0.65

matchCondition

-0.65

 nakalista

-0.64

POSITIVE LOGITS

the

0.73

 stuff

0.62

 ones

0.54

νες

0.52

ները

0.48

Layer

0.48

stans

0.45

big

0.44

やっぱり

0.44

那些

0.44

Activations Density 0.252%

elements relating to barriers and overcoming obstacles in various contexts

No Comments

No Known Activations