INDEX

Explanations

quotations in text

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "as" used to draw comparisons or quotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

yright

-0.74

width

-0.71

itiveness

-0.66

eeee

-0.65

oller

-0.64

Duration

-0.62

rower

-0.62

osc

-0.62

leness

-0.62

iton

-0.61

POSITIVE LOGITS

 follows

1.04

phy

0.83

pires

0.83

criptions

0.80

pell

0.79

 soon

0.78

pire

0.78

ĪĴ

0.77

pired

0.77

well

0.76

Activations Density 0.123%

quotations in text

phrases that include the word "as" used to draw comparisons or quotations

No Comments

No Known Activations