INDEX

Explanations

function calls related to converting or formatting data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

abestanden

-0.94

 bArr

-0.85

 Sada

-0.85

 subgoal

-0.84

Viitteet

-0.84

ItemBackground

-0.81

 Blackwood

-0.80

antMatchers

-0.79

Cio

-0.79

setPointSize

-0.78

POSITIVE LOGITS

ToString

0.97

 Hernandez

0.82

 Graff

0.74

Nuorodos

0.69

 ToString

0.67

 Randolph

0.65

RefreshLayout

0.64

 Gallardo

0.64

PMID

0.63

 Dodson

0.62

Activations Density 0.107%

function calls related to converting or formatting data types

No Comments

No Known Activations