INDEX

Explanations

names, likely locations or entities

oai_token-act-pair · gpt-3.5-turbo

references to specific geographic locations or associated institutions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

taboola

-0.81

ãĥīãĥ©ãĤ´ãĥ³

-0.77

ioxide

-0.69

ciating

-0.67

 Resp

-0.66

 Expend

-0.66

ctica

-0.64

BILITY

-0.61

 Vengeance

-0.60

=-=-=-=-

-0.59

POSITIVE LOGITS

inki

0.95

abee

0.86

acan

0.80

icultural

0.80

igans

0.79

quarters

0.79

awei

0.79

kamp

0.74

angs

0.71

iday

0.71

Activations Density 0.120%

names, likely locations or entities

references to specific geographic locations or associated institutions

No Comments

No Known Activations