INDEX

Explanations

phrases related to involvement in various activities or situations

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

nant

-0.64

omach

-0.64

 comparison

-0.61

helm

-0.61

opers

-0.61

edom

-0.60

nova

-0.60

els

-0.59

peat

-0.59

odo

-0.59

POSITIVE LOGITS

ioned

0.74

in

0.72

 therein

0.71

cius

0.70

itaire

0.70

 involved

0.69

 with

0.68

enza

0.67

 sidx

0.67

olved

0.65

Activations Density 0.062%

phrases related to involvement in various activities or situations

No Comments

No Known Activations