INDEX

Explanations

phrases or sentences related to prevention or prohibition

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "from" indicating origin or cause in various 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

 partName

-0.78

quickShipAvailable

-0.74

rites

-0.73

hello

-0.71

uid

-0.70

ixtures

-0.70

tons

-0.70

ratulations

-0.70

oy

-0.68

tops

-0.67

POSITIVE LOGITS

 afar

0.87

 scrimmage

0.85

 accessing

0.78

 capture

0.72

 extrad

0.69

 manufacture

0.68

 scratch

0.68

 entering

0.68

 exert

0.67

 anywhere

0.67

Activations Density 0.063%

phrases or sentences related to prevention or prohibition

instances of the phrase "from" indicating origin or cause in various contexts

No Comments

No Known Activations