INDEX

Explanations

actions or decisions that someone is allowed or able to make

oai_token-act-pair · gpt-3.5-turbo

phrases expressing consent or permission

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

ADS

-0.66

ruary

-0.66

lda

-0.66

livious

-0.64

ulp

-0.64

 NAACP

-0.63

wat

-0.63

OV

-0.62

Ori

-0.60

NR

-0.59

POSITIVE LOGITS

lich

0.82

.''.

0.77

 deems

0.69

 deem

0.65

Methods

0.65

.[

0.65

 Chimera

0.65

 indulge

0.64

.","

0.63

 thereof

0.62

Activations Density 0.246%

actions or decisions that someone is allowed or able to make

phrases expressing consent or permission

No Comments

No Known Activations