INDEX

Explanations

statements expressing opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

pronouns and expressions of intent or desire related to actions

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

abases

-0.65

plings

-0.64

 Ange

-0.63

ournal

-0.63

opolis

-0.63

blast

-0.63

 Prometheus

-0.62

WTC

-0.62

church

-0.62

bats

-0.61

POSITIVE LOGITS

 sorely

0.87

isse

0.69

 heard

0.66

 appreciated

0.64

 valued

0.64

 overheard

0.64

 dearly

0.63

ier

0.63

 wish

0.62

¶ħ

0.62

Activations Density 0.213%

statements expressing opinions or beliefs

pronouns and expressions of intent or desire related to actions

No Comments

No Known Activations