INDEX

Explanations

adjectives related to visual elements or representations

oai_token-act-pair · gpt-3.5-turbo

references to visual elements or qualities

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

doms

-0.89

unin

-0.83

qv

-0.80

olicy

-0.75

shire

-0.74

amaru

-0.71

uddin

-0.69

quist

-0.69

rocal

-0.69

gger

-0.68

POSITIVE LOGITS

izations

1.29

isations

1.23

isation

1.10

ized

1.05

izing

1.01

ization

1.00

izable

0.98

izer

0.97

izes

0.94

 representation

0.91

Activations Density 0.019%

adjectives related to visual elements or representations

references to visual elements or qualities

No Comments

No Known Activations