INDEX

Explanations

words related to a specific topic or theme

oai_token-act-pair · gpt-3.5-turbo

phrases indicating relationships or connections between topics

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

âķĲ

-0.84

aneers

-0.83

imates

-0.81

ifter

-0.79

\\\\\\\\

-0.75

arer

-0.73

oufl

-0.72

ARDS

-0.70

 Trees

-0.70

ardless

-0.70

POSITIVE LOGITS

 thereto

1.04

 ancest

0.86

ness

0.83

worldly

0.82

 unrelated

0.80

 mater

0.78

paren

0.76

itiz

0.75

lly

0.71

 additive

0.70

Activations Density 0.027%

words related to a specific topic or theme

phrases indicating relationships or connections between topics

No Comments

No Known Activations