INDEX

Explanations

information related to quantities or numerical values

oai_token-act-pair · gpt-3.5-turbo

instances of the word "about" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Peaks

-0.73

ocaly

-0.70

oly

-0.69

rift

-0.67

rang

-0.65

KK

-0.65

Write

-0.64

OGR

-0.64

SS

-0.64

enez

-0.62

POSITIVE LOGITS

 halfway

0.82

dinand

0.65

aleb

0.65

ials

0.65

pload

0.64

 midway

0.64

 coerc

0.63

urb

0.63

 migrating

0.63

Activations Density 0.155%

information related to quantities or numerical values

instances of the word "about" in various contexts

No Comments

No Known Activations