INDEX

Explanations

words related to medical conditions and treatments, specifically with emphasis on body parts and medical terminology

oai_token-act-pair · gpt-3.5-turbo

instances of numerical identifiers and certain medical terminology

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

Bug

-0.69

uphem

-0.67

 Chips

-0.63

FK

-0.63

ipers

-0.61

DJs

-0.59

 Roose

-0.59

Pink

-0.59

Story

-0.59

Sounds

-0.59

POSITIVE LOGITS

wagen

0.86

Ħ¢

0.80

efe

0.66

ensis

0.66

chnology

0.66

sted

0.64

İĭ

0.64

 Supplementary

0.63

anza

0.63

âĪĴ

0.62

Activations Density 0.220%

words related to medical conditions and treatments, specifically with emphasis on body parts and medical terminology

instances of numerical identifiers and certain medical terminology

No Comments

No Known Activations