INDEX

Explanations

quantities or lists of items

oai_token-act-pair · gpt-3.5-turbo

references to quantities and descriptions of elements in a technical or instructional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

usk

-0.83

acus

-0.81

aeus

-0.80

hirt

-0.78

iatus

-0.78

åħī

-0.76

ylum

-0.75

anse

-0.75

uca

-0.74

ansas

-0.74

POSITIVE LOGITS

 optimizations

1.61

 functions

1.54

 parameters

1.47

 dependencies

1.46

 modifications

1.44

 plugins

1.44

 variables

1.43

 commands

1.43

 settings

1.39

 tricks

1.39

Activations Density 0.253%

quantities or lists of items

references to quantities and descriptions of elements in a technical or instructional context

No Comments

No Known Activations