INDEX

Explanations

strong negative effects or consequences

oai_token-act-pair · gpt-3.5-turbo

terms indicating significant impacts or outcomes

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

atorium

-0.62

less

-0.59

âĸ¬

-0.58

 Canal

-0.58

info

-0.57

Entry

-0.55

ãĤ¨ãĥ«

-0.55

FN

-0.54

 Tycoon

-0.54

aaa

-0.53

POSITIVE LOGITS

poons

1.24

hips

1.15

paces

1.07

hip

1.03

mith

1.03

pring

1.02

pace

1.02

cale

0.97

uits

0.97

omething

0.96

Activations Density 0.419%

strong negative effects or consequences

terms indicating significant impacts or outcomes

No Comments

No Known Activations