INDEX

Explanations

references to law enforcement activities such as raids and police action

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "raid" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

å¦

-0.72

Perfect

-0.67

 Elev

-0.62

DonaldTrump

-0.62

 partName

-0.61

 Genie

-0.61

conservancy

-0.60

 Leilan

-0.60

pure

-0.60

 Acad

-0.60

POSITIVE LOGITS

 raid

1.12

 raids

1.06

 raided

0.99

ishly

0.98

 raiding

0.95

Raid

0.88

nard

0.85

rays

0.82

 seizure

0.78

 spree

0.77

Activations Density 0.012%

references to law enforcement activities such as raids and police action

occurrences of the word "raid" and its variations

No Comments

No Known Activations