INDEX

Explanations

terms related to technology companies or products

oai_token-act-pair · gpt-3.5-turbo

specific names of technology companies, operating systems, and related concepts

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

IFrame

Link

•Suppression Features Layer 8 GPT2 Small

No Comments

Negative Logits

 Lives

-1.04

 Benefit

-1.00

 Disorder

-0.97

 Month

-0.96

 Lover

-0.96

 Accountability

-0.95

 Lines

-0.94

 Matter

-0.94

 Thing

-0.94

 Clause

-0.93

POSITIVE LOGITS

 democr

0.82

arians

0.80

fortunately

0.79

 commons

0.78

tv

0.78

ensis

0.77

 franc

0.76

 americ

0.75

 academy

0.74

 communists

0.72

Activations Density 0.616%

terms related to technology companies or products

specific names of technology companies, operating systems, and related concepts

No Comments

No Known Activations