INDEX

Explanations

references to risky situations or actions

oai_token-act-pair · gpt-3.5-turbo

terms related to risk and speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Nap

-0.91

frey

-0.88

anooga

-0.86

yers

-0.85

chu

-0.85

oct

-0.84

pel

-0.83

ı

-0.82

upon

-0.81

orah

-0.79

POSITIVE LOGITS

 risky

1.06

 gamble

1.02

 gamb

0.98

 bets

0.94

 enterprises

0.90

 investments

0.88

 behaviors

0.87

 maneuvers

0.84

 behavior

0.84

 ventures

0.84

Activations Density 0.052%

references to risky situations or actions

terms related to risk and speculation

No Comments

No Known Activations