INDEX

Explanations

quantitative comparisons or superlatives

oai_token-act-pair · gpt-3.5-turbo

terms related to magnitude, significance, or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

din

-0.70

dfx

-0.66

mere

-0.63

agine

-0.62

 ASAP

-0.61

andel

-0.60

deep

-0.58

something

-0.58

 someday

-0.58

 Moons

-0.58

POSITIVE LOGITS

 overall

0.81

 (âĪĴ

0.75

 uptake

0.74

(-

0.73

 than

0.73

ikawa

0.71

 pronounced

0.70

luster

0.70

asca

0.65

 disapprove

0.65

Activations Density 0.286%

quantitative comparisons or superlatives

terms related to magnitude, significance, or impact

No Comments

No Known Activations