INDEX

Explanations

phrases related to a specific entity named "Ho"

oai_token-act-pair · gpt-3.5-turbo

references to a character or entity named 'Ho'

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

 confir

-0.81

 totality

-0.79

*/(

-0.76

CPC

-0.69

 agre

-0.67

 mileage

-0.67

omething

-0.67

 simul

-0.65

 anesthesia

-0.65

CTR

-0.64

POSITIVE LOGITS

pper

1.11

ppy

1.08

gey

1.07

oney

1.07

arding

1.06

LLOW

1.05

pping

0.99

oper

0.97

jo

0.96

Ho

0.96

Activations Density 0.016%

phrases related to a specific entity named "Ho"

references to a character or entity named 'Ho'

No Comments

No Known Activations