INDEX

Explanations

phrases related to rankings or categorizations, particularly those involving numbers

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a hierarchical or sequential relationship

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

leep

-0.50

steen

-0.49

estern

-0.49

rament

-0.49

 Legs

-0.47

rawdownloadcloneembedreportprint

-0.46

dq

-0.46

cers

-0.45

 berth

-0.45

uve

-0.44

POSITIVE LOGITS

inator

0.59

alg

0.56

and

0.51

icz

0.48

swick

0.48

ander

0.48

oran

0.47

ains

0.47

anders

0.45

alsh

0.45

Activations Density 0.284%

phrases related to rankings or categorizations, particularly those involving numbers

phrases that indicate a hierarchical or sequential relationship

No Comments

No Known Activations