INDEX

Explanations

conditional statements or comparisons indicating a threshold or limit

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 BoxFit

-1.14

 متعلقه

-0.94

 виправивши

-0.92

StreetMap

-0.92

StoryboardSegue

-0.90

ſelf

-0.88

 ―――――

-0.88

 FetchType

-0.86

DockStyle

-0.86

 ſche

-0.86

POSITIVE LOGITS

>=

0.69

ju

0.61

 relevance

0.59

 Relevance

0.59

 Seattle

0.56

geq

0.56

rotto

0.54

0.52

ை

0.52

!==

0.49

Activations Density 0.126%

conditional statements or comparisons indicating a threshold or limit

No Comments

No Known Activations