INDEX

Explanations

the name "Johansen"

oai_token-act-pair · gpt-3.5-turbo

the name "John" 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

dress

-0.82

 subsistence

-0.75

PLIED

-0.74

holders

-0.70

intendent

-0.66

ranean

-0.65

 compr

-0.64

BOOK

-0.64

 constrained

-0.63

©¶æ

-0.63

POSITIVE LOGITS

ansson

1.27

ansen

1.27

ani

1.05

anes

0.99

sin

0.94

annah

0.93

onen

0.93

Joh

0.91

anna

0.90

ans

0.90

Activations Density 0.016%

the name "Johansen"

the name "John" in various contexts

No Comments

No Known Activations