INDEX

Explanations

terms related to various physical locations and entities with the suffix "-gy" or "gy" at the end

oai_token-act-pair · gpt-3.5-turbo

references to energy and energy-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Archdemon

-0.74

 declass

-0.69

itures

-0.67

vou

-0.66

 enumer

-0.65

IBLE

-0.65

phabet

-0.63

ources

-0.61

NSA

-0.61

 conclud

-0.61

POSITIVE LOGITS

gy

1.15

gie

1.04

psy

0.99

gian

0.83

ny

0.82

cock

0.81

gom

0.80

cycles

0.79

gins

0.79

fixes

0.79

Activations Density 0.013%

terms related to various physical locations and entities with the suffix "-gy" or "gy" at the end

references to energy and energy-related concepts

No Comments

No Known Activations