INDEX

Explanations

descriptions of incidents related to suicide and its aftermath

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 👆

-0.60

 Oboe

-0.58

?«

-0.57

!«

-0.57

dci

-0.57

 chev

-0.55

 „,

-0.55

 blos

-0.54

*^

-0.54

 Græ

-0.53

POSITIVE LOGITS

 suicide

1.08

 suicidal

0.90

 suicides

0.89

suicide

0.87

 Suicide

0.85

 sarili

0.84

Suicide

0.82

 suic

0.80

自殺

0.70

 Bekasi

0.69

Activations Density 0.234%

descriptions of incidents related to suicide and its aftermath

No Comments

No Known Activations