INDEX

Explanations

words related to leaves

oai_token-act-pair · gpt-3.5-turbo

references to leaves 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

PDATE

-0.90

ALLY

-0.70

nels

-0.69

 Revel

-0.67

CHR

-0.65

ourke

-0.64

cedes

-0.63

ENTION

-0.63

 guiActiveUnfocused

-0.63

AUD

-0.63

POSITIVE LOGITS

let

1.21

lets

1.10

leaf

0.98

iard

0.97

leted

0.95

grass

0.93

overs

0.92

 lettuce

0.92

worm

0.87

roots

0.86

Activations Density 0.038%

words related to leaves

references to leaves in various contexts

No Comments

No Known Activations