INDEX

Explanations

personal pronouns 'I' or 'we' followed by hypothetical situations

oai_token-act-pair · gpt-3.5-turbo

first-person singular pronouns in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MpServer

-0.66

Reviewer

-0.64

ULTS

-0.60

Balt

-0.58

FAR

-0.58

 Neutral

-0.57

 Paradise

-0.57

mobi

-0.56

 Gleaming

-0.56

Sharp

-0.56

POSITIVE LOGITS

 ever

0.85

'm

0.76

 succeed

0.75

 weren

0.74

 wanna

0.74

 hypot

0.74

 hadn

0.73

agu

0.72

 someday

0.72

 EVER

0.71

Activations Density 0.073%

personal pronouns 'I' or 'we' followed by hypothetical situations

first-person singular pronouns in various contexts

No Comments

No Known Activations