INDEX

Explanations

dates in the format of month and year, with stronger activations for specific dates and numeric timestamps

oai_token-act-pair · gpt-3.5-turbo

dates and numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥ£

-0.60

Ã¨re

-0.56

Äĩ

-0.55

ËĪ

-0.54

ãĤ§

-0.53

è£

-0.52

è»

-0.51

steen

-0.50

kas

-0.50

POSITIVE LOGITS

];

0.57

]."

0.53

];

0.50

inent

0.50

 rusher

0.49

 respectively

0.45

']

0.45

 Cummings

0.45

artifacts

0.44

};

0.44

Activations Density 0.383%

dates in the format of month and year, with stronger activations for specific dates and numeric timestamps

dates and numerical data

No Comments

No Known Activations