INDEX

Explanations

mentions of trees

oai_token-act-pair · gpt-3.5-turbo

references to trees and related concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

glomer

-0.91

arcer

-0.80

rontal

-0.76

ione

-0.71

ities

-0.71

oice

-0.69

abwe

-0.69

farious

-0.68

olitan

-0.66

ersive

-0.64

POSITIVE LOGITS

 canopy

1.14

frog

1.04

beard

1.02

 trees

1.02

 tree

0.95

Hug

0.95

yard

0.93

 stump

0.92

 Trees

0.91

 trunk

0.90

Activations Density 0.024%

mentions of trees

references to trees and related concepts

No Comments

No Known Activations