INDEX

Explanations

words related to traps

oai_token-act-pair · gpt-3.5-turbo

references to traps, both literal and metaphorical

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

edly

-0.88

issance

-0.85

sis

-0.77

eda

-0.73

verty

-0.67

league

-0.67

Merit

-0.65

eds

-0.64

care

-0.63

lihood

-0.63

POSITIVE LOGITS

door

1.45

doors

1.33

finding

0.88

 traps

0.87

idon

0.86

trap

0.86

 trap

0.81

 Hole

0.79

ERY

0.77

 Trap

0.76

Activations Density 0.035%

words related to traps

references to traps, both literal and metaphorical

No Comments

No Known Activations