INDEX

Explanations

keywords associated with the effects of actions on health or well-being

oai_token-act-pair · gpt-3.5-turbo

terms related to the positive and negative impacts on health and well-being

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

buck

-0.81

cled

-0.77

ailable

-0.77

illon

-0.74

¤

-0.69

Hide

-0.68

fund

-0.67

etter

-0.67

gs

-0.66

cling

-0.66

POSITIVE LOGITS

 effects

1.14

 consequences

0.99

 outcomes

0.94

 effect

0.94

 impacts

0.91

 influences

0.88

 Effects

0.88

 affects

0.88

effects

0.86

 outcome

0.85

Activations Density 0.101%

keywords associated with the effects of actions on health or well-being

terms related to the positive and negative impacts on health and well-being

No Comments

No Known Activations