INDEX

Explanations

phrases or words related to significant achievements or events

oai_token-act-pair · gpt-3.5-turbo

references to significant achievements or benchmarks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

©¶æ

-1.07

olls

-0.82

otto

-0.81

amina

-0.76

obe

-0.73

piracy

-0.72

 rented

-0.70

ells

-0.70

resp

-0.68

olly

-0.68

POSITIVE LOGITS

 milestone

1.37

 milestones

1.25

 celebrations

0.85

 achievement

0.81

 hurdle

0.79

 accomplishment

0.77

 celebration

0.75

 achievements

0.75

enary

0.71

 hurdles

0.71

Activations Density 0.004%

phrases or words related to significant achievements or events

references to significant achievements or benchmarks

No Comments

No Known Activations