INDEX

Explanations

phrases related to beliefs, values, and actions

oai_token-act-pair · gpt-3.5-turbo

statements reflecting personal experiences and beliefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Examination

-0.74

 Nanto

-0.74

 Ferry

-0.70

"]=>

-0.70

 Solution

-0.69

 Fishing

-0.69

 Adjusted

-0.69

Comb

-0.66

 Compensation

-0.66

 Checking

-0.64

POSITIVE LOGITS

 otherwise

1.22

 already

1.17

 rightfully

1.06

rir

1.00

 previously

0.99

 traditionally

0.92

 ordinarily

0.90

 desperately

0.88

 normally

0.87

 deems

0.86

Activations Density 0.411%

phrases related to beliefs, values, and actions

statements reflecting personal experiences and beliefs

No Comments

No Known Activations