INDEX

Explanations

instructions or prompts indicating the beginning of an activity or process

oai_token-act-pair · gpt-3.5-turbo

phrases related to beginning or initializing tasks or actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugs

-0.72

owl

-0.71

othy

-0.66

olog

-0.66

uts

-0.64

etry

-0.63

hang

-0.63

obal

-0.62

atu

-0.62

houses

-0.62

POSITIVE LOGITS

nings

0.87

 anew

0.84

NING

0.73

 experimenting

0.72

 navigating

0.70

 exerc

0.70

ctory

0.69

 exploring

0.69

 practicing

0.69

 thinking

0.68

Activations Density 0.031%

instructions or prompts indicating the beginning of an activity or process

phrases related to beginning or initializing tasks or actions

No Comments

No Known Activations