INDEX

Explanations

phrases related to translation or conversion

oai_token-act-pair · gpt-3.5-turbo

instances of the word "into" and variations of turning or transforming one thing into another

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

Reviewed

-0.97

hov

-0.74

FactoryReloaded

-0.74

areth

-0.73

cens

-0.72

ysis

-0.70

minus

-0.69

ibu

-0.67

listed

-0.67

usp

-0.67

POSITIVE LOGITS

 usable

1.03

 tangible

0.96

 practical

0.94

 concrete

0.92

 actual

0.86

 subsequent

0.83

 meaningful

0.82

 real

0.80

 coherent

0.74

 form

0.74

Activations Density 0.345%

phrases related to translation or conversion

instances of the word "into" and variations of turning or transforming one thing into another

No Comments

No Known Activations