INDEX

Explanations

phrases that introduce a shift in focus or provide context for a subsequent statement

oai_token-act-pair · gpt-3.5-turbo

references to illumination or clarity in the context of discussions or events

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

lycer

-0.74

irie

-0.74

irlf

-0.72

pload

-0.70

itals

-0.68

sis

-0.68

asus

-0.68

hesive

-0.66

kefeller

-0.65

 Carnegie

-0.65

POSITIVE LOGITS

enment

1.02

ening

0.89

 circumstances

0.85

 questioning

0.80

ened

0.78

weights

0.76

weight

0.73

 circumstance

0.73

bringer

0.72

lessness

0.68

Activations Density 0.016%

phrases that introduce a shift in focus or provide context for a subsequent statement

references to illumination or clarity in the context of discussions or events

No Comments

No Known Activations