INDEX

Explanations

words or phrases indicating comparison or contrast

oai_token-act-pair · gpt-3.5-turbo

statements that emphasize the nature or quality of a subject

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

actory

-0.76

otte

-0.71

oided

-0.70

igraph

-0.70

rongh

-0.68

itches

-0.68

ievers

-0.66

ced

-0.65

commit

-0.64

icipated

-0.63

POSITIVE LOGITS

 admittedly

1.10

why

1.04

 understandable

1.03

 basically

1.01

 probably

0.98

 ironic

0.97

 kinda

0.97

 certainly

0.95

 obviously

0.94

 presumably

0.91

Activations Density 0.142%

words or phrases indicating comparison or contrast

statements that emphasize the nature or quality of a subject

No Comments

No Known Activations