INDEX

Explanations

phrases related to keys or key-related actions

oai_token-act-pair · gpt-3.5-turbo

technical terms related to keys and keyframes in digital contexts

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

 coli

-0.70

ModLoader

-0.69

abama

-0.69

 Veil

-0.66

ynes

-0.65

 Tend

-0.64

 Glac

-0.63

 Examination

-0.63

 Ashes

-0.62

iless

-0.62

POSITIVE LOGITS

ioch

0.78

 ignition

0.76

 pedals

0.76

tein

0.70

chains

0.68

chain

0.68

ondo

0.67

 steering

0.67

 levers

0.66

 keys

0.66

Activations Density 0.407%

phrases related to keys or key-related actions

technical terms related to keys and keyframes in digital contexts

No Comments

No Known Activations