INDEX

Explanations

words related to character encoding

oai_token-act-pair · gpt-3.5-turbo

specific characters and their variations within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 rack

-0.69

LOAD

-0.64

 Reloaded

-0.63

 Mirror

-0.63

 trickle

-0.63

CBO

-0.61

 torque

-0.61

 wave

-0.61

 Rasmussen

-0.60

 Norton

-0.60

POSITIVE LOGITS

acters

2.13

char

1.34

isma

0.91

anka

0.86

kun

0.84

vill

0.83

sty

0.83

anye

0.82

unte

0.82

thal

0.81

Activations Density 0.009%

words related to character encoding

specific characters and their variations within a text

No Comments

No Known Activations