INDEX

Explanations

mentions of guests

oai_token-act-pair · gpt-3.5-turbo

instances of the word "guest" 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

 conflic

-0.75

 Rite

-0.73

agically

-0.73

nces

-0.71

cale

-0.68

bis

-0.66

 Skydragon

-0.65

 Rossi

-0.65

ooks

-0.63

 Roche

-0.62

POSITIVE LOGITS

Guest

0.93

 guest

0.84

 guests

0.84

roach

0.79

inar

0.79

 Guest

0.78

RTX

0.78

itors

0.75

 Guests

0.73

esses

0.73

Activations Density 0.023%

mentions of guests

instances of the word "guest" in various contexts

No Comments

No Known Activations