INDEX

Explanations

names or terms related to a specific person or place, possibly "Ry" related

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the name "Ry" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hurricanes

-0.76

IBLE

-0.75

 Edison

-0.75

 Mandela

-0.70

ãĥ¼ãĥĨãĤ£

-0.66

enegger

-0.65

 Fairfax

-0.65

imately

-0.64

resso

-0.63

FTA

-0.63

POSITIVE LOGITS

anche

0.94

Å«

0.92

©¶æ¥µ

0.88

uling

0.87

urnal

0.87

obi

0.86

Ry

0.85

Ry

0.83

aky

0.82

stad

0.82

Activations Density 0.012%

names or terms related to a specific person or place, possibly "Ry" related

the repeated mention of the name "Ry" in various contexts

No Comments

No Known Activations