INDEX

Explanations

terms related to matrices and specific proper nouns like "Matrix" and "Terminator"

oai_token-act-pair · gpt-3.5-turbo

terms related to matrices and associated computational 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IGH

-0.86

vous

-0.77

OPLE

-0.76

FUL

-0.75

sweet

-0.74

cker

-0.73

IRD

-0.72

biased

-0.70

odied

-0.70

hig

-0.69

POSITIVE LOGITS

 Reloaded

1.05

eering

1.02

rices

0.94

 multiplication

0.87

 Matrix

0.87

eers

0.79

 matrix

0.76

umbai

0.75

ingly

0.75

 aperture

0.71

Activations Density 0.010%

terms related to matrices and specific proper nouns like "Matrix" and "Terminator"

terms related to matrices and associated computational concepts

No Comments

No Known Activations