INDEX

Explanations

mathematical symbols and formatting used in LaTeX or mathematical expressions

oai_token-act-pair · gpt-3.5-turbo

special characters and formatting symbols used in coding or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

nesday

-0.86

anium

-0.80

 Beir

-0.79

itionally

-0.78

ijah

-0.78

eele

-0.74

 Shroud

-0.72

 Canter

-0.72

itives

-0.71

imeters

-0.71

POSITIVE LOGITS

cffffcc

1.09

NW

0.88

hl

0.77

0.76

Pg

0.72

cule

0.72

Î»

0.70

cffff

0.70

gy

0.70

hidden

0.69

Activations Density 0.011%

mathematical symbols and formatting used in LaTeX or mathematical expressions

special characters and formatting symbols used in coding or markup languages

No Comments

No Known Activations