INDEX

Explanations

references to people named Laura

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Laura."

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

cffff

-0.95

MENTS

-0.78

rated

-0.76

*/(

-0.74

cffffcc

-0.71

haps

-0.68

flies

-0.67

ministic

-0.66

nces

-0.66

Ü

-0.66

POSITIVE LOGITS

 Palmer

1.05

 Jane

0.94

 Loren

0.81

Vo

0.80

Ing

0.78

gdala

0.78

 Weather

0.78

 Bates

0.77

 Bloom

0.77

anne

0.76

Activations Density 0.022%

references to people named Laura

occurrences of the name "Laura."

No Comments

No Known Activations