INDEX

Explanations

varying names, possibly of notable individuals, that are at the center of news or articles

oai_token-act-pair · gpt-3.5-turbo

names of people and their affiliations or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

acters

-0.66

artments

-0.56

prus

-0.55

eals

-0.55

tyr

-0.55

LEASE

-0.55

 captcha

-0.54

idences

-0.54

ensional

-0.54

/+

-0.54

POSITIVE LOGITS

*,

0.98

0.83

QC

0.82

?,

0.81

!,

0.78

Jr

0.76

0.75

Sr

0.75

,,

0.74

,...

0.70

Activations Density 0.305%

varying names, possibly of notable individuals, that are at the center of news or articles

names of people and their affiliations or roles

No Comments

No Known Activations