INDEX

Explanations

terms related to risk assessment and consequences

oai_token-act-pair · gpt-3.5-turbo

phrases related to risk and harm associated with substances or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Malays

-0.66

 (Â£

-0.61

 Malaysia

-0.61

review

-0.61

 Ashton

-0.60

 lately

-0.59

 Saudis

-0.58

 Rosenstein

-0.58

 yesterday

-0.58

 Defence

-0.58

POSITIVE LOGITS

ãĥĩãĤ£

0.80

itto

0.70

 behavi

0.68

 incent

0.66

sonian

0.65

eming

0.63

 tremend

0.63

inently

0.62

 sshd

0.62

 suspic

0.62

Activations Density 0.982%

terms related to risk assessment and consequences

phrases related to risk and harm associated with substances or actions

No Comments

No Known Activations