INDEX

Explanations

words related to security measures or locks

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Lock" and "Block" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

PsyNetMessage

-0.80

ãĤ¼ãĤ¦ãĤ¹

-0.78

theless

-0.76

è£

-0.73

è¡

-0.72

èĢħ

-0.71

BLE

-0.70

ãĥ¬

-0.70

éĹ

-0.70

éĥ

-0.70

POSITIVE LOGITS

heed

0.97

yard

0.81

backer

0.81

yer

0.81

 Dome

0.79

Eye

0.77

ern

0.75

 Launcher

0.75

ert

0.75

acre

0.74

Activations Density 0.015%

words related to security measures or locks

instances of the word "Lock" and "Block" in various contexts

No Comments

No Known Activations