INDEX

Explanations

phrases related to detailed processes or tasks

oai_token-act-pair · gpt-3.5-turbo

phrases related to processes and the effort required to execute tasks

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

olitics

-0.82

cit

-0.80

ults

-0.76

ledged

-0.69

Sport

-0.68

ippy

-0.68

sided

-0.67

endo

-0.67

nil

-0.66

ynes

-0.66

POSITIVE LOGITS

 determining

1.83

 figuring

1.76

 obtaining

1.70

 selecting

1.69

 constructing

1.68

 identifying

1.67

 designing

1.64

 verifying

1.64

 locating

1.63

 preparing

1.61

Activations Density 0.392%

phrases related to detailed processes or tasks

phrases related to processes and the effort required to execute tasks

No Comments

No Known Activations