INDEX

Explanations

phrases indicating a continuation or progression in a story

oai_token-act-pair · gpt-3.5-turbo

repeated phrases indicating continuity or ongoing narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

bats

-0.78

ointed

-0.68

footed

-0.68

wit

-0.68

agnetic

-0.63

ishops

-0.63

haps

-0.61

Walk

-0.61

onomic

-0.61

liest

-0.61

POSITIVE LOGITS

 BELOW

0.86

 Below

0.66

advertisement

0.65

 trending

0.64

 transcript

0.61

TBD

0.61

CLASSIFIED

0.61

ource

0.59

 Bris

0.58

 Vaugh

0.57

Activations Density 0.012%

phrases indicating a continuation or progression in a story

repeated phrases indicating continuity or ongoing narrative context

No Comments

No Known Activations