INDEX

Explanations

terms related to underlying issues or structures

oai_token-act-pair · gpt-3.5-turbo

references to foundational or core concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cture

-0.90

asia

-0.81

alde

-0.79

ooters

-0.77

ishers

-0.75

cker

-0.73

ellen

-0.73

avis

-0.72

hops

-0.72

UNCH

-0.72

POSITIVE LOGITS

 infrastructure

0.86

 assumptions

0.85

 structure

0.84

 principles

0.84

 assumption

0.83

 structures

0.83

 fundamentals

0.83

 underlying

0.83

tons

0.81

 layers

0.80

Activations Density 0.023%

terms related to underlying issues or structures

references to foundational or core concepts

No Comments

No Known Activations