INDEX

Explanations

references to software or technology-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

agher

-0.91

naire

-0.78

uating

-0.75

bow

-0.71

lain

-0.71

erent

-0.70

ewitness

-0.69

Ze

-0.67

onna

-0.67

abouts

-0.65

POSITIVE LOGITS

 RAID

0.91

works

0.90

 installer

0.90

 interfaces

0.87

bytes

0.82

kit

0.82

upd

0.81

 glitches

0.81

Deploy

0.80

 patents

0.80

Activations Density 0.040%

references to software or technology-related terms

terms related to software

No Comments

No Known Activations