INDEX

Explanations

negative words or phrases

oai_token-act-pair · gpt-3.5-turbo

terms related to negative impacts or consequences

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

plain

-0.94

nington

-0.88

DOM

-0.86

aido

-0.80

frey

-0.79

xxxxxxxx

-0.79

uble

-0.78

amaru

-0.78

ingham

-0.77

ablished

-0.76

POSITIVE LOGITS

 consequences

1.14

 repercussions

1.07

 gearing

1.06

 impacts

1.04

 impact

1.04

 feedback

1.04

 publicity

1.03

 affect

0.99

 reperc

0.98

 consequence

0.95

Activations Density 0.079%

negative words or phrases

terms related to negative impacts or consequences

No Comments

No Known Activations