INDEX

Explanations

phrases related to expressing opinions or uttering words

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate speech or communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

shoot

-0.75

pleting

-0.69

onut

-0.67

equipped

-0.64

gart

-0.63

amate

-0.62

pend

-0.62

xtap

-0.61

 Destroyer

-0.61

 typh

-0.59

POSITIVE LOGITS

 goodbye

1.31

 aloud

1.22

 about

1.00

 loudly

0.91

 afterwards

0.89

 uttered

0.83

 beforehand

0.83

 afterward

0.82

 publicly

0.81

 sarcast

0.80

Activations Density 0.073%

phrases related to expressing opinions or uttering words

phrases that indicate speech or communication

No Comments

No Known Activations