INDEX

Explanations

the word stem 'gl' followed by a varying number

oai_token-act-pair · gpt-3.5-turbo

variations of the word "glide" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hyde

-0.90

TAIN

-0.85

ÃįÃį

-0.77

ÄŁ

-0.76

cles

-0.71

BLIC

-0.69

ITAL

-0.69

OLOGY

-0.67

ãĤ®

-0.66

cules

-0.66

POSITIVE LOGITS

itz

1.10

itched

1.02

adiator

1.00

immer

0.96

amping

0.95

ib

0.95

anz

0.95

ashing

0.92

uffed

0.92

itter

0.92

Activations Density 0.011%

the word stem 'gl' followed by a varying number

variations of the word "glide" and its related forms

No Comments

No Known Activations