INDEX

Explanations

instances where action is taken or things are treated in a specific way

oai_token-act-pair · gpt-3.5-turbo

technical terms and concepts related to computing and programming

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

crew

-0.81

podcast

-0.76

Roz

-0.74

 Bravo

-0.70

isine

-0.67

christ

-0.67

 Ezek

-0.66

liv

-0.65

gyn

-0.65

 Militia

-0.64

POSITIVE LOGITS

 syntax

1.16

 recursive

1.14

 semantics

1.07

 runtime

1.06

 debugging

1.05

 abstraction

1.02

 invari

1.02

 interpol

1.02

 synt

1.01

 initialization

1.01

Activations Density 0.513%

instances where action is taken or things are treated in a specific way

technical terms and concepts related to computing and programming

No Comments

No Known Activations