INDEX

Explanations

instances of the word "low"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "low."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

arium

-0.83

 critically

-0.76

Asia

-0.67

ãĤ·ãĥ£

-0.66

andum

-0.64

tnc

-0.63

*/(

-0.61

ADRA

-0.61

 Freak

-0.60

 verbally

-0.59

POSITIVE LOGITS

low

1.17

est

0.96

enthal

0.82

down

0.82

lower

0.80

ered

0.78

stairs

0.78

ener

0.76

Low

0.74

sted

0.74

Activations Density 0.004%

instances of the word "low"

occurrences of the word "low."

No Comments

No Known Activations