INDEX

Explanations

interviews mentioned in text

oai_token-act-pair · gpt-3.5-turbo

phrases related to interviews

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

 Goods

-0.77

ple

-0.72

sels

-0.68

ciplinary

-0.67

wagen

-0.67

axy

-0.65

 mercy

-0.64

ffe

-0.63

 goods

-0.63

oud

-0.62

POSITIVE LOGITS

 interview

0.89

 interviews

0.80

ees

0.80

 booth

0.79

reon

0.79

 aired

0.78

athon

0.77

 conducted

0.75

 SHOW

0.71

 newsp

0.70

Activations Density 0.017%

interviews mentioned in text

phrases related to interviews

No Comments

No Known Activations