INDEX

Explanations

terms related to codenames or codifying

oai_token-act-pair · gpt-3.5-turbo

references to "cod" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Parish

-0.80

IELD

-0.76

ACP

-0.71

olicy

-0.67

INTER

-0.66

 Prosper

-0.63

 Pradesh

-0.63

HY

-0.63

zzi

-0.62

LV

-0.61

POSITIVE LOGITS

ename

1.34

ependent

1.17

irect

1.04

epend

1.01

ependence

1.00

ãĥį

0.98

ãĥĥãĥī

0.97

ified

0.95

gers

0.94

ãĥ¼ãĥ

0.92

Activations Density 0.022%

terms related to codenames or codifying

references to "cod" in various contexts

No Comments

No Known Activations