INDEX

Explanations

words related to organizations or projects, especially those involving technical fields

oai_token-act-pair · gpt-3.5-turbo

references to organizations

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

 evict

-0.68

teen

-0.66

words

-0.65

 derivatives

-0.64

Fine

-0.63

©¶æ

-0.63

 Buchanan

-0.57

 notch

-0.57

DOE

-0.57

scene

-0.56

POSITIVE LOGITS

ensen

1.09

roup

1.04

uments

1.03

ersen

1.01

sky

0.97

enson

0.96

raphic

0.92

asms

0.91

ued

0.90

lishes

0.90

Activations Density 0.021%

words related to organizations or projects, especially those involving technical fields

references to organizations

No Comments

No Known Activations