INDEX

Explanations

personal pronouns and verbs related to allowing or permitting actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of first-person and second-person pronouns

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

 Lump

-0.69

govtrack

-0.65

olate

-0.63

hips

-0.63

ĪĴ

-0.63

angel

-0.62

Sax

-0.61

 riddled

-0.59

ÑĢ

-0.57

gall

-0.57

POSITIVE LOGITS

 access

0.78

SpaceEngineers

0.73

 unrestricted

0.73

 unlimited

0.70

 peek

0.69

 lapse

0.68

 freely

0.67

 deduction

0.66

 flexibility

0.65

 sake

0.65

Activations Density 0.192%

personal pronouns and verbs related to allowing or permitting actions

occurrences of first-person and second-person pronouns

No Comments

No Known Activations