INDEX

Explanations

references related to the television show "Doctor Who"

oai_token-act-pair · gpt-3.5-turbo

references to the "Doctor Who" television series and its characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

tera

-0.71

 total

-0.69

rily

-0.68

LOAD

-0.66

mission

-0.65

creen

-0.63

ndra

-0.62

 airspace

-0.61

TER

-0.61

minist

-0.61

POSITIVE LOGITS

Who

1.15

 Strange

0.89

sonian

0.88

 Crusher

0.81

obic

0.78

é¾įå

0.78

ate

0.77

 Fate

0.76

Zh

0.75

Who

0.75

Activations Density 0.049%

references related to the television show "Doctor Who"

references to the "Doctor Who" television series and its characters

No Comments

No Known Activations