INDEX

Explanations

texts related to holding law enforcement accountable for their actions

oai_token-act-pair · gpt-3.5-turbo

sentences that begin with "There is" or similar constructions

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

LDL

-0.59

ONSORED

-0.59

 toxin

-0.58

nib

-0.57

 recipient

-0.57

 Armored

-0.56

EA

-0.56

 tolerant

-0.56

oint

-0.55

cup

-0.54

POSITIVE LOGITS

abouts

1.43

upon

1.25

after

1.06

fore

0.95

ngth

0.88

FORE

0.86

phabet

0.82

zbollah

0.81

nsic

0.80

ibaba

0.79

Activations Density 0.108%

texts related to holding law enforcement accountable for their actions

sentences that begin with "There is" or similar constructions

No Comments

No Known Activations