INDEX

Explanations

words related to knowledge or understanding

oai_token-act-pair · gpt-3.5-turbo

the conjunctions "and" and "or."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Squid

-0.67

heit

-0.65

MET

-0.63

 steroids

-0.60

 Jackets

-0.59

nc

-0.58

 Rainbow

-0.58

Ens

-0.58

 Copper

-0.57

 Arms

-0.56

POSITIVE LOGITS

rogen

0.84

romeda

0.80

rogens

0.79

 analyse

0.73

 diagnose

0.73

 smelled

0.71

 hear

0.70

ryn

0.70

dden

0.70

sound

0.70

Activations Density 0.175%

words related to knowledge or understanding

the conjunctions "and" and "or."

No Comments

No Known Activations