INDEX

Explanations

the action of pretending or feigning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "pretend" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.74

âĨĳ

-0.70

 GOODMAN

-0.65

cutting

-0.65

ccording

-0.62

srf

-0.62

å£«

-0.61

 palms

-0.61

sbm

-0.60

vez

-0.60

POSITIVE LOGITS

 innocence

0.83

ulence

0.70

entious

0.69

 forgot

0.68

pas

0.65

 otherwise

0.63

 pret

0.63

 Â¯

0.62

 falsely

0.62

 inco

0.62

Activations Density 0.022%

the action of pretending or feigning

instances of the word "pretend" and its variations

No Comments

No Known Activations