INDEX

Explanations

words related to military operations, particularly the term "raid."

oai_token-act-pair · gpt-3.5-turbo

references to raids

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

å¦

-0.76

 Extrem

-0.67

verified

-0.64

Past

-0.63

éĸ

-0.63

Geo

-0.63

reviewed

-0.62

Nat

-0.62

mis

-0.62

Perfect

-0.61

POSITIVE LOGITS

 raid

1.22

 raids

1.19

 raiding

1.10

ishly

0.99

 raided

0.98

Raid

0.89

ings

0.79

raid

0.79

rays

0.75

 sweeps

0.74

Activations Density 0.008%

words related to military operations, particularly the term "raid."

references to raids

No Comments

No Known Activations