INDEX

Explanations

terms related to monitoring and processes

oai_token-act-pair · gpt-3.5-turbo

specific institutional or procedural terms and references

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 toget

-0.82

olson

-0.77

etsk

-0.76

 disg

-0.74

ĸļ

-0.71

 aloud

-0.70

antically

-0.69

tyr

-0.69

 notor

-0.69

 livest

-0.68

POSITIVE LOGITS

 Manager

1.14

 Removal

1.11

 Units

1.09

 Disorder

1.06

 Initiative

1.05

 Rating

1.04

 Specialist

1.04

 Sets

1.02

 Version

1.01

 Designs

1.00

Activations Density 0.315%

terms related to monitoring and processes

specific institutional or procedural terms and references

No Comments

No Known Activations