INDEX

Explanations

numerical ranges or limits

oai_token-act-pair · gpt-3.5-turbo

phrases indicating maximum limits or quantities

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

birds

-0.66

brook

-0.66

Moving

-0.64

rats

-0.64

went

-0.64

Wiz

-0.63

NEY

-0.62

 Perspective

-0.59

Reviewer

-0.59

Smart

-0.58

POSITIVE LOGITS

pload

1.04

capacity

0.79

perty

0.75

 date

0.74

0.73

kw

0.71

thirds

0.71

atever

0.70

abyte

0.70

undreds

0.65

Activations Density 0.039%

numerical ranges or limits

phrases indicating maximum limits or quantities

No Comments

No Known Activations