INDEX

Explanations

phrases related to technology and information, particularly in informational contexts

oai_token-act-pair · gpt-3.5-turbo

titles or strong descriptors related to evaluations or ratings of various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 tremend

-0.69

 toget

-0.68

cli

-0.65

antry

-0.64

hement

-0.62

etheless

-0.62

 sidew

-0.60

irez

-0.60

 wiser

-0.59

>[

-0.59

POSITIVE LOGITS

 Madness

0.78

 Collection

0.77

Mem

0.77

 Legends

0.76

 Rocks

0.75

 Society

0.74

 Seconds

0.74

 Remix

0.72

Ltd

0.72

 Awards

0.71

Activations Density 1.783%

phrases related to technology and information, particularly in informational contexts

titles or strong descriptors related to evaluations or ratings of various subjects

No Comments

No Known Activations