INDEX

Explanations

instances of the word "assume" in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "assume" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Sche

-0.71

psey

-0.70

emetery

-0.70

cgi

-0.70

Shipping

-0.63

 Watching

-0.62

alez

-0.61

nels

-0.61

mary

-0.60

turn

-0.60

POSITIVE LOGITS

 assume

1.09

 assumed

0.86

 assuming

0.83

 assumes

0.82

 presume

0.79

eret

0.71

IRT

0.68

 assum

0.68

inet

0.67

 assumptions

0.65

Activations Density 0.013%

instances of the word "assume" in various contexts

instances of the word "assume" and its variations in various contexts

No Comments

No Known Activations