INDEX

Explanations

phrases related to fantasy or science fiction movie titles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

staking

-0.82

sterdam

-0.68

furt

-0.67

 toget

-0.66

 indulge

-0.66

fully

-0.66

Downloadha

-0.65

rade

-0.65

icho

-0.65

etheless

-0.65

POSITIVE LOGITS

Law

0.78

 same

0.78

 Philippines

0.78

 Rockies

0.77

 largest

0.76

 smallest

0.76

 Past

0.75

 Balance

0.74

 Hill

0.74

 Netherlands

0.74

Activations Density 0.294%

phrases related to fantasy or science fiction movie titles

occurrences of the word "the."

No Comments

No Known Activations