INDEX

Explanations

mentions of the term "Marawi"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations or names associated with political events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Else

-0.78

nces

-0.70

matter

-0.69

wife

-0.64

 Gemini

-0.64

wives

-0.63

cession

-0.60

graph

-0.59

 Ceres

-0.59

 Curiosity

-0.58

POSITIVE LOGITS

awi

1.17

uala

0.86

aii

0.86

akening

0.86

oux

0.85

uthor

0.84

uth

0.84

oken

0.84

chuk

0.82

doms

0.82

Activations Density 0.010%

mentions of the term "Marawi"

mentions of specific geographical locations or names associated with political events

No Comments

No Known Activations