INDEX

Explanations

references to visits to different locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "to" in various contexts related to visits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ictive

-0.84

ials

-0.73

ropy

-0.72

ention

-0.72

DN

-0.72

ancial

-0.71

acters

-0.71

iction

-0.71

ictions

-0.71

rss

-0.70

POSITIVE LOGITS

 Disneyland

0.89

tnc

0.81

 Mecca

0.77

 vacation

0.74

 abroad

0.73

 Nanto

0.72

home

0.71

Moy

0.71

 Mongolia

0.71

 visit

0.71

Activations Density 0.138%

references to visits to different locations

occurrences of the phrase "to" in various contexts related to visits

No Comments

No Known Activations