INDEX

Explanations

list or rank items, often with a superlative descriptor like "top" or "best"

oai_token-act-pair · gpt-3.5-turbo

references to popular rankings or "top" lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ĸļ

-0.83

ighter

-0.78

adra

-0.76

hyde

-0.76

atum

-0.74

ctor

-0.69

strength

-0.69

matter

-0.68

riber

-0.68

icum

-0.68

POSITIVE LOGITS

 moments

1.11

 quotes

1.10

 stories

0.99

 locations

0.94

 places

0.93

 examples

0.93

 intersections

0.93

 unsolved

0.92

 topics

0.91

 websites

0.90

Activations Density 0.201%

list or rank items, often with a superlative descriptor like "top" or "best"

references to popular rankings or "top" lists

No Comments

No Known Activations