INDEX

Explanations

financial and statistical terms

oai_token-act-pair · gpt-3.5-turbo

terms related to quantitative data and reporting

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

laughs

-0.76

tis

-0.72

Returns

-0.68

votes

-0.66

Else

-0.66

tains

-0.65

Temperature

-0.65

needs

-0.63

HAM

-0.61

 Kills

-0.61

POSITIVE LOGITS

are

1.48

 aren

1.45

 weren

1.43

 were

1.41

 seem

1.17

 illustrate

1.16

 imply

1.14

 constitute

1.13

 include

1.13

 indicate

1.12

Activations Density 0.418%

financial and statistical terms

terms related to quantitative data and reporting

No Comments

No Known Activations