INDEX

Explanations

phrases related to problem-solving or decision-making

oai_token-act-pair · gpt-3.5-turbo

instances of the word "figure" and its various forms used in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

eatures

-0.80

ibaba

-0.79

etimes

-0.75

ewitness

-0.74

emies

-0.73

ankind

-0.72

athi

-0.71

ributes

-0.71

nces

-0.70

etheus

-0.69

POSITIVE LOGITS

 skating

0.89

 prominently

0.81

out

0.73

istically

0.70

ĸ

0.67

ħ

0.66

sonian

0.66

stock

0.64

share

0.63

ling

0.62

Activations Density 0.017%

phrases related to problem-solving or decision-making

instances of the word "figure" and its various forms used in context

No Comments

No Known Activations