INDEX

Explanations

images or photographs mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

alties

-0.69

mental

-0.67

mails

-0.66

zig

-0.66

utenberg

-0.66

ally

-0.66

omsky

-0.65

few

-0.64

cession

-0.64

sense

-0.64

POSITIVE LOGITS

 above

1.15

 below

1.08

 pictured

0.97

above

0.97

 Above

0.94

 circa

0.91

 smiling

0.89

below

0.87

 flanked

0.87

 atop

0.85

Activations Density 0.032%

images or photographs mentioned in the text

No Comments

No Known Activations