INDEX

Explanations

comparative adjectives indicating improvement or preference

oai_token-act-pair · gpt-3.5-turbo

expressions of improvement or superiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

landers

-0.65

çļ

-0.62

iasm

-0.61

 Guid

-0.60

shire

-0.59

redd

-0.58

erity

-0.58

chains

-0.57

reciation

-0.57

hemy

-0.57

POSITIVE LOGITS

 than

1.59

 Than

1.13

than

1.12

 suited

1.00

 behaved

0.82

 situated

0.77

 paced

0.74

served

0.73

iated

0.69

anced

0.68

Activations Density 0.089%

comparative adjectives indicating improvement or preference

expressions of improvement or superiority

No Comments

No Known Activations