INDEX

Explanations

references to actions or characteristics related to a specific group of people

oai_token-act-pair · gpt-3.5-turbo

references to the word "they" indicating a focus on people or groups being discussed

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

 Eleven

-0.89

CCC

-0.85

 Glob

-0.72

Tad

-0.70

 Kinn

-0.70

UTC

-0.67

 Globe

-0.67

 Atlantis

-0.66

 Cable

-0.66

 Flan

-0.66

POSITIVE LOGITS

're

1.28

've

1.03

selves

1.02

'll

0.99

self

0.91

 selves

0.89

 themselves

0.89

own

0.87

 perceive

0.85

 deserve

0.85

Activations Density 0.229%

references to actions or characteristics related to a specific group of people

references to the word "they" indicating a focus on people or groups being discussed

No Comments

No Known Activations