INDEX

Explanations

proper names, likely focusing on individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns or significant names

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

 guiActiveUnfocused

-0.95

[&

-0.82

 Nanto

-0.81

Interstitial

-0.76

ĸļ

-0.75

 misunder

-0.74

 Cthulhu

-0.74

 Guant

-0.70

 foreseeable

-0.69

;;;;;;;;;;;;

-0.68

POSITIVE LOGITS

ricks

0.95

ant

0.95

int

0.86

oops

0.83

ants

0.82

ante

0.81

atar

0.79

ances

0.78

bs

0.78

ices

0.78

Activations Density 0.385%

proper names, likely focusing on individuals

proper nouns or significant names

No Comments

No Known Activations