INDEX

Explanations

years or dates expressed in numeric format

oai_token-act-pair · gpt-3.5-turbo

specific years mentioned 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

ularity

-0.86

paralle

-0.70

egal

-0.66

onge

-0.66

imon

-0.64

iaries

-0.64

anamo

-0.64

ndra

-0.63

RAM

-0.62

lace

-0.62

POSITIVE LOGITS

0.72

 Augustus

0.68

âĢķ

0.67

 census

0.65

 onwards

0.65

0.64

0.63

Activations Density 0.036%

years or dates expressed in numeric format

specific years mentioned in the text

No Comments

No Known Activations