INDEX

Explanations

negative words related to criticism or disapproval

oai_token-act-pair · gpt-3.5-turbo

negative descriptors or phrases related to unfavorable qualities

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

ĸļ

-0.96

raltar

-0.77

ensional

-0.77

earchers

-0.75

ittees

-0.75

theless

-0.75

htaking

-0.74

conservancy

-0.73

eston

-0.73

xual

-0.72

POSITIVE LOGITS

dies

1.09

dest

1.08

die

1.04

ger

0.96

gered

0.93

GES

0.88

ged

0.86

ges

0.86

 karma

0.86

 luck

0.85

Activations Density 0.029%

negative words related to criticism or disapproval

negative descriptors or phrases related to unfavorable qualities

No Comments

No Known Activations