INDEX

Explanations

phrases or words that indicate praise or admiration

oai_token-act-pair · gpt-3.5-turbo

words associated with accolades or positive recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 cooker

-0.79

xus

-0.76

 residue

-0.75

thia

-0.72

omaly

-0.72

vati

-0.71

hing

-0.71

heed

-0.70

 allergies

-0.69

 diapers

-0.68

POSITIVE LOGITS

 praise

0.81

 hailed

0.75

 praises

0.74

 aloud

0.74

 acclaim

0.70

Rated

0.70

 praised

0.69

 virtues

0.69

 applauded

0.69

ESPN

0.69

Activations Density 0.035%

phrases or words that indicate praise or admiration

words associated with accolades or positive recognition

No Comments

No Known Activations