INDEX

Explanations

phrases related to social issues or causes

oai_token-act-pair · gpt-3.5-turbo

phrases related to social issues and advocacy

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

Spec

-0.86

otide

-0.80

erenn

-0.80

ramid

-0.78

claimer

-0.77

aeus

-0.77

 teasp

-0.77

NN

-0.77

Figure

-0.76

ascript

-0.76

POSITIVE LOGITS

 teenagers

1.11

 millennials

1.11

 women

1.08

 cyclists

1.07

 gays

1.06

 addicts

1.06

 celebrities

1.06

 girls

1.03

 youths

1.03

 transgender

1.02

Activations Density 0.677%

phrases related to social issues or causes

phrases related to social issues and advocacy

No Comments

No Known Activations