INDEX

Explanations

words related to safety or security

oai_token-act-pair · gpt-3.5-turbo

terms related to safety and secure environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

issance

-0.78

naire

-0.77

yss

-0.75

fred

-0.70

 Revenue

-0.64

anche

-0.62

 XIII

-0.61

ataka

-0.60

 Fiber

-0.60

hiba

-0.59

POSITIVE LOGITS

 havens

1.12

haven

1.00

keeping

0.97

inventoryQuantity

0.93

 haven

0.90

 harbor

0.89

 Haven

0.82

house

0.81

 deposit

0.80

 harbour

0.80

Activations Density 0.050%

words related to safety or security

terms related to safety and secure environments

No Comments

No Known Activations