INDEX

Explanations

proper nouns related to famous figures or places

oai_token-act-pair · gpt-3.5-turbo

large quantities of commas or punctuation, suggesting a focus on lists or multiple points in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

oir

-0.60

EO

-0.56

irection

-0.55

rom

-0.54

iku

-0.53

ore

-0.52

ord

-0.52

atively

-0.52

ishly

-0.52

rome

-0.51

POSITIVE LOGITS

 respectively

0.79

 âĵĺ

0.65

zbollah

0.60

udeb

0.60

usalem

0.58

itsch

0.56

 Belfast

0.53

luaj

0.53

Fla

0.52

 Sammy

0.50

Activations Density 0.380%

proper nouns related to famous figures or places

large quantities of commas or punctuation, suggesting a focus on lists or multiple points in the text

No Comments

No Known Activations