INDEX

Explanations

references to personal experiences or opinions

oai_token-act-pair · gpt-3.5-turbo

the word "this" in various contexts

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

ãĤ¹ãĥĪ

-0.89

Īè

-0.80

ãĥĥ

-0.77

¨

-0.75

Ĭ±

-0.75

ãĥ©ãĥ³

-0.69

ivas

-0.69

aus

-0.69

©¶æ¥µ

-0.69

Ħ

-0.69

POSITIVE LOGITS

 trope

0.99

 week

0.95

 sucker

0.93

guy

0.89

 kind

0.87

 sort

0.85

 month

0.84

 nifty

0.80

 type

0.78

 year

0.78

Activations Density 0.206%

references to personal experiences or opinions

the word "this" in various contexts

No Comments

No Known Activations