INDEX

Explanations

phrases related to mysterious elements or situations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "mystery" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

attery

-0.89

baugh

-0.88

obe

-0.74

olt

-0.74

ornia

-0.73

minster

-0.72

estine

-0.71

boa

-0.71

erate

-0.70

ocate

-0.70

POSITIVE LOGITS

 solved

1.13

 unsolved

0.93

 mystery

0.87

 surrounds

0.87

 Flavoring

0.85

 solving

0.83

 puzzle

0.82

 Mystery

0.80

 puzzles

0.79

 Shack

0.78

Activations Density 0.041%

phrases related to mysterious elements or situations

occurrences of the word "mystery" in various contexts

No Comments

No Known Activations