INDEX

Explanations

words with the prefix "dis-" indicating negation or reversal

oai_token-act-pair · gpt-3.5-turbo

words related to disappointment or unfavorable situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glers

-0.70

Reviewer

-0.68

 Damn

-0.66

 Parm

-0.65

 Kinnikuman

-0.65

 scratch

-0.63

swick

-0.60

 Franks

-0.60

 Archdemon

-0.60

 Beyond

-0.60

POSITIVE LOGITS

comfort

1.08

ruption

1.07

rup

1.04

cipl

1.04

appointed

1.02

abling

0.99

dis

0.97

licted

0.95

quiet

0.95

abled

0.94

Activations Density 0.005%

words with the prefix "dis-" indicating negation or reversal

words related to disappointment or unfavorable situations

No Comments

No Known Activations