INDEX

Explanations

locations or cities

oai_token-act-pair · gpt-3.5-turbo

names of cities and locations

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

hement

-0.74

slot

-0.74

inventory

-0.74

earance

-0.71

lihood

-0.71

arget

-0.69

thereum

-0.69

activation

-0.69

ittal

-0.68

mentioned

-0.68

POSITIVE LOGITS

 winters

1.10

 Nights

1.02

 Skies

1.01

 Avenue

0.88

 Style

0.86

 Comic

0.86

 skyline

0.86

 circa

0.85

 natives

0.84

 Beautiful

0.83

Activations Density 0.355%

locations or cities

names of cities and locations

No Comments

No Known Activations