INDEX

Explanations

phrases related to particular names, like "Gleason"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Gleason" and related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

raints

-0.91

rador

-0.73

 Palestin

-0.70

anmar

-0.70

raint

-0.68

oola

-0.68

ierrez

-0.67

ournal

-0.67

icipated

-0.67

 Patriarch

-0.66

POSITIVE LOGITS

vey

0.90

rette

0.86

ptive

0.85

bt

0.83

ber

0.82

fred

0.81

\\\\\\\\\\\\\\\\

0.80

efully

0.80

bilt

0.79

lem

0.78

Activations Density 0.010%

phrases related to particular names, like "Gleason"

mentions of the word "Gleason" and related references

No Comments

No Known Activations