INDEX

Explanations

references to various levels of participation or implication in certain actions or events

oai_token-act-pair · gpt-3.5-turbo

references to involvement in various activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sell

-0.71

 Balanced

-0.70

Jet

-0.70

Float

-0.69

\\\\\\\\

-0.64

 Rapt

-0.62

imb

-0.61

Lev

-0.61

Leon

-0.61

Spa

-0.60

POSITIVE LOGITS

enza

0.91

 involvement

0.88

annel

0.82

ioned

0.81

atform

0.76

itaire

0.74

oice

0.73

iveness

0.73

rity

0.72

hips

0.71

Activations Density 0.016%

references to various levels of participation or implication in certain actions or events

references to involvement in various activities or events

No Comments

No Known Activations