INDEX

Explanations

words related to spokesperson roles or individuals representing organizations

oai_token-act-pair · gpt-3.5-turbo

words related to spokespersons and their statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 exception

-0.67

's

-0.65

 submission

-0.65

 Governments

-0.63

 Jehovah

-0.63

 Government

-0.62

Phys

-0.62

 Physicians

-0.61

 Lucky

-0.61

 Scotia

-0.61

POSITIVE LOGITS

pace

1.81

hip

1.63

chool

1.62

creen

1.62

hips

1.55

hift

1.54

paces

1.53

peed

1.53

pring

1.51

hirt

1.46

Activations Density 0.253%

words related to spokesperson roles or individuals representing organizations

words related to spokespersons and their statements

No Comments

No Known Activations