INDEX

Explanations

terms related to physical locations or descriptions of physical structures

oai_token-act-pair · gpt-3.5-turbo

words related to "ground" or foundational concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Marketable

-0.79

volent

-0.74

orum

-0.72

ority

-0.70

aird

-0.70

omas

-0.65

emonic

-0.63

CBI

-0.63

 Peel

-0.61

oshop

-0.61

POSITIVE LOGITS

hog

1.50

sheet

1.07

floor

1.04

breaking

1.03

sw

1.03

cover

1.00

nut

0.97

lings

0.97

sheets

0.95

nuts

0.92

Activations Density 0.024%

terms related to physical locations or descriptions of physical structures

words related to "ground" or foundational concepts

No Comments

No Known Activations