INDEX

Explanations

words related to violent incidents or crimes

oai_token-act-pair · gpt-3.5-turbo

references to violent incidents or assaults

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ETA

-0.71

BuyableInstoreAndOnline

-0.67

dit

-0.66

FORMATION

-0.66

theless

-0.64

}}}

-0.63

UTION

-0.62

 mineral

-0.62

ERE

-0.61

SOURCE

-0.61

POSITIVE LOGITS

 spree

1.05

 perpetrated

0.94

 attack

0.87

attack

0.87

 attacks

0.86

 against

0.84

abad

0.82

ivist

0.78

iveness

0.77

 assault

0.76

Activations Density 0.039%

words related to violent incidents or crimes

references to violent incidents or assaults

No Comments

No Known Activations