INDEX

Explanations

proper nouns that seem to be related to news headlines or events

oai_token-act-pair · gpt-3.5-turbo

words or phrases related to directives, lists, and connections in reporting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

imum

-0.74

itol

-0.69

oller

-0.67

ivalry

-0.67

eah

-0.65

natureconservancy

-0.64

erest

-0.63

aea

-0.63

thia

-0.62

urus

-0.61

POSITIVE LOGITS

Downloadha

0.81

upon

0.78

 removable

0.68

pared

0.67

 è£ıè

0.66

paren

0.65

deb

0.63

Gy

0.62

 insane

0.62

skilled

0.61

Activations Density 0.405%

proper nouns that seem to be related to news headlines or events

words or phrases related to directives, lists, and connections in reporting

No Comments

No Known Activations