INDEX

Explanations

clearly delineated sections in a document

oai_token-act-pair · gpt-3.5-turbo

repeated phrases or structural patterns in the text

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

stones

-0.79

rovers

-0.72

dn

-0.71

tops

-0.70

cards

-0.67

hawks

-0.66

DB

-0.66

Chain

-0.66

ahime

-0.65

abad

-0.63

POSITIVE LOGITS

 successive

1.18

 iteration

0.87

where

0.85

 individual

0.83

 subsequent

0.78

 individually

0.78

THING

0.75

 succeeding

0.74

 weekday

0.74

omore

0.72

Activations Density 0.033%

clearly delineated sections in a document

repeated phrases or structural patterns in the text

No Comments

No Known Activations