INDEX

Explanations

discussions related to freedom of expression

oai_token-act-pair · gpt-3.5-turbo

references to the concept of freedom, particularly freedom of expression

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eor

-0.80

ergy

-0.78

ents

-0.74

mers

-0.72

itated

-0.71

ded

-0.71

ENTS

-0.70

liam

-0.69

 Dynasty

-0.67

senal

-0.67

POSITIVE LOGITS

bies

0.90

 roam

0.90

 guaranteed

0.85

 freedoms

0.77

 Fighters

0.77

 freedom

0.76

boot

0.76

freedom

0.75

 afforded

0.74

 unrestricted

0.73

Activations Density 0.023%

discussions related to freedom of expression

references to the concept of freedom, particularly freedom of expression

No Comments

No Known Activations