INDEX

Explanations

words related to medical or physiological conditions

oai_token-act-pair · gpt-3.5-turbo

specific scientific terms and concepts related to anatomy and physiology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

staking

-0.71

Else

-0.68

hetically

-0.62

 damning

-0.60

 Gators

-0.60

cially

-0.60

DOE

-0.59

 fruitful

-0.58

 Nieto

-0.58

FUL

-0.58

POSITIVE LOGITS

ombat

0.92

tones

0.86

clerosis

0.72

 Orchestra

0.69

sts

0.68

ibrary

0.68

rings

0.67

uga

0.67

andowski

0.66

 Measures

0.66

Activations Density 0.641%

words related to medical or physiological conditions

specific scientific terms and concepts related to anatomy and physiology

No Comments

No Known Activations