INDEX

Explanations

references to specific abbreviations in medical contexts

oai_token-act-pair · gpt-3.5-turbo

instances of references to ratings or evaluations

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

anova

-0.75

amins

-0.73

oola

-0.66

 srfAttach

-0.65

atu

-0.65

achu

-0.64

»Ĵ

-0.64

ashtra

-0.63

TextColor

-0.62

rawdownloadcloneembedreportprint

-0.62

POSITIVE LOGITS

 coli

1.04

0.69

 Moss

0.69

 Romero

0.67

existent

0.66

 fashioned

0.66

tainment

0.63

 Manning

0.62

geist

0.62

 Proxy

0.62

Activations Density 0.039%

references to specific abbreviations in medical contexts

instances of references to ratings or evaluations

No Comments

No Known Activations