INDEX

Explanations

words related to risks and taking risks

oai_token-act-pair · gpt-3.5-turbo

references to risk and risk-related concepts

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

gdala

-0.71

atters

-0.71

issance

-0.71

Dispatch

-0.70

poons

-0.68

Bed

-0.65

gian

-0.65

glers

-0.65

vez

-0.64

isan

-0.63

POSITIVE LOGITS

 aversion

1.02

iest

0.93

taking

0.93

 factors

0.91

 posed

0.90

 incurred

0.85

iness

0.83

 factor

0.82

 mitigation

0.78

lessness

0.76

Activations Density 0.049%

words related to risks and taking risks

references to risk and risk-related concepts

No Comments

No Known Activations