INDEX

Explanations

phrases related to applying pressure or causing influence

oai_token-act-pair · gpt-3.5-turbo

phrases related to the concept of pressure, particularly in a societal or systemic context

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

SourceFile

-0.76

mpeg

-0.74

 Klux

-0.70

acements

-0.69

aces

-0.69

ults

-0.67

imilar

-0.67

ISA

-0.66

olf

-0.65

lene

-0.63

POSITIVE LOGITS

erous

1.21

 behalf

1.00

 shoulders

0.84

shore

0.83

coming

0.79

rez

0.73

ibaba

0.72

 tyres

0.69

 brakes

0.69

top

0.68

Activations Density 0.068%

phrases related to applying pressure or causing influence

phrases related to the concept of pressure, particularly in a societal or systemic context

No Comments

No Known Activations