INDEX

Explanations

names of authors and publishers

oai_token-act-pair · gpt-3.5-turbo

author names and publication details in academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

interstitial

-0.86

 applicable

-0.73

olves

-0.70

itol

-0.69

 upside

-0.67

overs

-0.66

alde

-0.66

pread

-0.64

Bound

-0.63

odic

-0.62

POSITIVE LOGITS

 supra

1.20

et

1.04

Jr

0.86

LLP

0.84

 Associates

0.84

JA

0.83

JJ

0.81

rahim

0.76

 Constantin

0.75

LLC

0.75

Activations Density 0.090%

names of authors and publishers

author names and publication details in academic references

No Comments

No Known Activations