INDEX

Explanations

phrases related to negation or prohibition

oai_token-act-pair · gpt-3.5-turbo

negations and expressions of absence or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

INESS

-0.68

Previous

-0.67

 Fields

-0.64

 ALWAYS

-0.63

 milliseconds

-0.63

 personalities

-0.62

ARY

-0.61

Indiana

-0.59

Current

-0.58

 somewhere

-0.57

POSITIVE LOGITS

vae

0.98

zu

0.97

vez

0.96

lez

0.94

tu

0.94

nda

0.93

aque

0.91

ppa

0.90

lla

0.90

kan

0.89

Activations Density 0.062%

phrases related to negation or prohibition

negations and expressions of absence or denial

No Comments

No Known Activations