INDEX

Explanations

numerical values embedded within text

oai_token-act-pair · gpt-3.5-turbo

numerical identifiers or values associated with images or captions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

graduate

-0.67

sed

-0.66

itionally

-0.65

lag

-0.62

pick

-0.62

development

-0.61

shapeshifter

-0.61

aimon

-0.61

rugged

-0.61

termin

-0.60

POSITIVE LOGITS

 Photos

0.87

 embed

0.74

 IMAGES

0.72

 caption

0.71

 Pict

0.69

 toggle

0.68

 Cosponsors

0.68

embed

0.67

 depiction

0.67

 Thumbnails

0.67

Activations Density 0.046%

numerical values embedded within text

numerical identifiers or values associated with images or captions

No Comments

No Known Activations