INDEX

Explanations

words related to medical conditions and treatments

oai_token-act-pair · gpt-3.5-turbo

terms related to categorization and classification

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Magikarp

-0.81

Ô

-0.74

ikuman

-0.71

 largeDownload

-0.69

cember

-0.67

 Collider

-0.67

EStreamFrame

-0.63

 Pigs

-0.63

 hover

-0.61

uminati

-0.60

POSITIVE LOGITS

ogyn

0.76

esthesia

0.72

achus

0.69

ail

0.68

rex

0.68

gency

0.68

hetic

0.64

ilit

0.64

onductor

0.63

andise

0.63

Activations Density 0.088%

words related to medical conditions and treatments

terms related to categorization and classification

No Comments

No Known Activations