INDEX

Explanations

repeated phrases that indicate a duration of time

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

phrases indicating a specific period of time or event occurrence

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

usercontent

-0.86

ilty

-0.64

 predict

-0.59

 owed

-0.59

aires

-0.58

ards

-0.57

 reckoned

-0.57

BILITY

-0.56

 killer

-0.56

 implicated

-0.55

POSITIVE LOGITS

neath

0.92

 interviews

0.88

cest

0.84

ventory

0.81

 conversations

0.77

flation

0.73

spection

0.72

drawn

0.71

math

0.71

 this

0.71

Activations Density 0.108%

repeated phrases that indicate a duration of time

phrases indicating a specific period of time or event occurrence

No Comments

No Known Activations