INDEX

Explanations

verbs related to reversing or negating actions

oai_token-act-pair · gpt-3.5-turbo

terms related to reversing actions or decisions

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

colo

-0.88

asio

-0.84

chens

-0.79

rical

-0.77

croft

-0.73

olson

-0.72

fighter

-0.71

rikes

-0.70

rano

-0.69

ritic

-0.68

POSITIVE LOGITS

 undo

0.94

 undone

0.87

 havoc

0.83

issance

0.75

 disabling

0.69

 strand

0.67

 erase

0.65

balance

0.63

 unravel

0.62

undo

0.62

Activations Density 0.014%

verbs related to reversing or negating actions

terms related to reversing actions or decisions

No Comments

No Known Activations