INDEX

Explanations

phrases indicating location or position

oai_token-act-pair · gpt-3.5-turbo

phrases indicating location or existence in a context

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

STA

-0.67

 Logged

-0.67

 Crusher

-0.62

CVE

-0.60

 Torrent

-0.58

 thor

-0.58

 Advertisement

-0.56

0000000000000000

-0.55

 Sear

-0.55

Day

-0.55

POSITIVE LOGITS

 periphery

0.91

idth

0.80

gypt

0.75

 vicinity

0.73

between

0.71

animate

0.71

 continuum

0.71

eneg

0.66

Middle

0.66

oots

0.66

Activations Density 0.097%

phrases indicating location or position

phrases indicating location or existence in a context

No Comments

No Known Activations