INDEX

Explanations

phrases related to recovery from physical or psychological trauma or conditions

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

nic

-0.70

chery

-0.69

colo

-0.67

OPA

-0.67

ullah

-0.58

sky

-0.58

bis

-0.57

bill

-0.57

owler

-0.57

fer

-0.56

POSITIVE LOGITS

ilitating

0.86

overy

0.80

chwitz

0.73

ains

0.73

aining

0.72

ees

0.72

 recover

0.71

 recovered

0.71

strap

0.70

Lost

0.70

Activations Density 0.069%

phrases related to recovery from physical or psychological trauma or conditions

No Comments

No Known Activations