INDEX

Explanations

terms related to a structured classification system, particularly focusing on "Axis" labels

oai_token-act-pair · gpt-3.5-turbo

references to psychiatric diagnostic axes and associated terms

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

esters

-1.00

nan

-0.90

aned

-0.88

kered

-0.81

porting

-0.81

mitted

-0.80

ributed

-0.80

mer

-0.79

regor

-0.79

scripts

-0.77

POSITIVE LOGITS

llor

0.87

 mund

0.86

 crank

0.71

illary

0.68

 Lans

0.66

 sickness

0.65

EMENT

0.63

Ax

0.60

 overflow

0.59

 axis

0.59

Activations Density 0.064%

terms related to a structured classification system, particularly focusing on "Axis" labels

references to psychiatric diagnostic axes and associated terms

No Comments

No Known Activations