INDEX

Explanations

instances of the word "immunity."

oai_token-act-pair · gpt-3.5-turbo

terms related to legal immunity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

VOL

-0.71

 Forth

-0.64

las

-0.63

 aest

-0.63

glas

-0.63

Cent

-0.61

gt

-0.60

 Wood

-0.60

cht

-0.60

 Vand

-0.60

POSITIVE LOGITS

 immunity

4.45

 Immunity

3.08

 immune

1.72

immune

1.53

 impunity

1.47

 immun

1.38

 exemption

1.25

 Immun

1.22

 exemptions

1.20

 antibodies

1.20

Activations Density 0.015%

instances of the word "immunity."

terms related to legal immunity

No Comments

No Known Activations