INDEX

Explanations

instances of the word "even" followed by a comparative or superlative adjective

oai_token-act-pair · gpt-3.5-turbo

the word "even" 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 @ 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

rend

-0.91

HCR

-0.76

raud

-0.65

Ã°

-0.64

Band

-0.63

ync

-0.61

~~~~~~~~

-0.61

ected

-0.60

RFC

-0.60

othy

-0.59

POSITIVE LOGITS

 remotely

0.98

handed

0.96

 though

0.78

handedly

0.77

 MORE

0.70

ivari

0.70

tho

0.70

 numbered

0.69

ront

0.66

 moderately

0.62

Activations Density 0.063%

instances of the word "even" followed by a comparative or superlative adjective

the word "even" in various contexts

No Comments

No Known Activations