INDEX

Explanations

references to credits and specific individuals in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "include" and its variations in lists or examples

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

alty

-0.73

aptic

-0.72

orce

-0.72

uters

-0.71

enser

-0.70

ifact

-0.69

atal

-0.69

uers

-0.69

wan

-0.68

ould

-0.68

POSITIVE LOGITS

:'

0.69

:#

0.69

:-

0.63

 flashbacks

0.62

 weddings

0.61

 those

0.61

 prominently

0.60

 Daredevil

0.60

 Blaster

0.59

Activations Density 0.054%

references to credits and specific individuals in various contexts

instances of the word "include" and its variations in lists or examples

No Comments

No Known Activations