INDEX

Explanations

possible consequences or implications of a given scenario

oai_token-act-pair · gpt-3.5-turbo

conditional statements and hypothetical situations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

alks

-0.69

plates

-0.65

ateurs

-0.65

perty

-0.62

rike

-0.61

rete

-0.60

 Hear

-0.60

chuk

-0.60

ancock

-0.59

tor

-0.59

POSITIVE LOGITS

 incidentally

0.87

SPONSORED

0.85

 understandable

0.85

 admittedly

0.83

wcsstore

0.81

quickShipAvailable

0.81

 exacerbated

0.79

ECA

0.75

 ironically

0.74

 inconvenient

0.74

Activations Density 0.235%

possible consequences or implications of a given scenario

conditional statements and hypothetical situations

No Known Activations