INDEX

Explanations

specific abbreviations related to technology or military

oai_token-act-pair · gpt-3.5-turbo

references to "AU" or "au" 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 @ 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

ows

-0.92

Ö¼

-0.90

ocks

-0.86

ivas

-0.77

tons

-0.77

idates

-0.77

ipes

-0.74

iffs

-0.74

sburgh

-0.73

appers

-0.73

POSITIVE LOGITS

cedes

0.90

iliary

0.89

HAHAHAHA

0.80

chwitz

0.79

vertis

0.76

HAHA

0.75

interstitial

0.74

querque

0.74

mble

0.73

gypt

0.72

Activations Density 0.031%

specific abbreviations related to technology or military

references to "AU" or "au" in various contexts

No Comments

No Known Activations