INDEX

Explanations

proper nouns that contain "ho" with varying contexts such as names, places, and events

oai_token-act-pair · gpt-3.5-turbo

words related to specific surnames and their associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

BILITIES

-0.72

ãĥīãĥ©ãĤ´ãĥ³

-0.71

cffffcc

-0.71

ĻĤ

-0.70

ADRA

-0.67

 reversible

-0.67

 unfocusedRange

-0.67

ioxide

-0.65

 tert

-0.64

POSITIVE LOGITS

warts

0.97

pedia

0.86

ratulations

0.83

inki

0.80

gow

0.79

velt

0.70

arest

0.68

rm

0.68

angs

0.68

monary

0.68

Activations Density 0.113%

proper nouns that contain "ho" with varying contexts such as names, places, and events

words related to specific surnames and their associations

No Comments

No Known Activations