INDEX

Explanations

words related to progression or improvement

oai_token-act-pair · gpt-3.5-turbo

the indefinite article "a" and quantify instances of it in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

packages

-0.80

evidence

-0.75

 indicators

-0.75

items

-0.73

adding

-0.72

casts

-0.69

/-

-0.66

 indications

-0.64

bots

-0.63

ðŁ

-0.63

POSITIVE LOGITS

venge

1.47

rouse

1.12

 predetermined

0.89

 manageable

0.86

 convenient

0.83

 distant

0.82

 rainy

0.82

 whopping

0.81

 detriment

0.80

 bunch

0.80

Activations Density 0.128%

words related to progression or improvement

the indefinite article "a" and quantify instances of it in varying contexts

No Comments

No Known Activations