INDEX

Explanations

references to the TV show "Doctor Who."

oai_token-act-pair · gpt-3.5-turbo

mentions of "Doctor Who."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rations

-0.87

ģ«

-0.76

âĸ¬

-0.68

ration

-0.66

 shaping

-0.66

 heating

-0.65

 drying

-0.65

 adequ

-0.63

 prin

-0.61

rator

-0.60

POSITIVE LOGITS

soever

1.05

verse

0.78

emouth

0.77

stone

0.73

abouts

0.73

 Came

0.73

itte

0.73

iw

0.71

istle

0.71

isen

0.71

Activations Density 0.017%

references to the TV show "Doctor Who."

mentions of "Doctor Who."

No Comments

No Known Activations