INDEX

Explanations

phrases related to becoming accustomed to something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "used" 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

 Helsinki

-0.68

olulu

-0.65

 Houth

-0.64

hani

-0.61

 Tale

-0.60

hra

-0.59

 Zurich

-0.59

 irrad

-0.59

 issu

-0.59

 assassinated

-0.58

POSITIVE LOGITS

fully

1.00

ience

0.92

fulness

0.88

ãĥ¬

0.85

ibles

0.85

ãĥ¼ãĥĨãĤ£

0.85

ãĥ©

0.79

 partName

0.78

ãĤ¢

0.78

ien

0.77

Activations Density 0.075%

phrases related to becoming accustomed to something

instances of the word "used" in various contexts

No Comments

No Known Activations