INDEX

Explanations

specific numerical and symbol patterns

oai_token-act-pair · gpt-3.5-turbo

various numerical or coded data elements, possibly related to sports statistics or event timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 toget

-0.69

 veins

-0.67

 faithfully

-0.61

 ingred

-0.61

 proport

-0.60

 Brach

-0.60

 amounted

-0.59

 convol

-0.58

 once

-0.58

 wholes

-0.58

POSITIVE LOGITS

anyahu

0.80

meier

0.74

Interstitial

0.70

aniel

0.70

avez

0.68

cation

0.67

 Narr

0.67

ACTED

0.65

omsky

0.65

Activations Density 0.138%

specific numerical and symbol patterns

various numerical or coded data elements, possibly related to sports statistics or event timestamps

No Comments

No Known Activations