INDEX

Explanations

numerical quantities and measurements

oai_token-act-pair · gpt-3.5-turbo

occurrences of quantitative data or numerical references

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.73

 Indeed

-0.71

Indeed

-0.69

 distinguishing

-0.69

ãĢĳ

-0.68

 acquaint

-0.67

 Identification

-0.66

 possesses

-0.66

 prompting

-0.66

 adherents

-0.66

POSITIVE LOGITS

 fuckin

1.12

['

1.02

 crappy

0.97

 gonna

0.95

 blah

0.93

âĢ¦"

0.90

 eighty

0.90

 shitty

0.89

 âĢ¦"

0.88

 blackout

0.88

Activations Density 0.514%

numerical quantities and measurements

occurrences of quantitative data or numerical references

No Comments

No Known Activations