INDEX

Explanations

programming-related keywords and syntax symbols

oai_token-act-pair · gpt-3.5-turbo

variable and function names in code syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

quished

-0.83

atform

-0.80

 Pearce

-0.76

 Garry

-0.76

eteria

-0.76

 Manson

-0.74

JPM

-0.71

 Sachs

-0.70

 Infect

-0.69

 Mercy

-0.69

POSITIVE LOGITS

dict

1.07

chance

1.03

state

0.99

modules

0.99

default

0.98

gradient

0.98

usable

0.96

enabled

0.96

module

0.95

blank

0.95

Activations Density 0.025%

programming-related keywords and syntax symbols

variable and function names in code syntax

No Comments

No Known Activations