INDEX

Explanations

phrases related to actions causing negative outcomes or harm

oai_token-act-pair · gpt-3.5-turbo

instances of causation leading to negative outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Horizons

-0.61

itar

-0.61

 demos

-0.60

gaard

-0.60

 follow

-0.59

oped

-0.59

 Transition

-0.58

 text

-0.58

itarian

-0.57

 interviews

-0.57

POSITIVE LOGITS

 causing

3.32

 inflicting

1.97

 preventing

1.84

 harming

1.78

 injuring

1.77

 affecting

1.73

 disrupting

1.72

 ruining

1.71

 triggering

1.71

 provoking

1.70

Activations Density 0.025%

phrases related to actions causing negative outcomes or harm

instances of causation leading to negative outcomes

No Comments

No Known Activations