INDEX

Explanations

words related to physical harm or damage

oai_token-act-pair · gpt-3.5-turbo

terms related to death and mortality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

XY

-0.74

FFFF

-0.73

HCR

-0.67

ERG

-0.66

advertisement

-0.65

herty

-0.63

AUD

-0.63

XXXX

-0.62

 Potential

-0.62

Specific

-0.61

POSITIVE LOGITS

 mort

1.37

uary

1.02

ally

0.84

gue

0.81

 veter

0.80

 srfAttach

0.79

 surpr

0.78

 dism

0.77

osate

0.76

 embr

0.76

Activations Density 0.010%

words related to physical harm or damage

terms related to death and mortality

No Comments

No Known Activations