INDEX

Explanations

phrases related to logging and entries

oai_token-act-pair · gpt-3.5-turbo

terms related to logging and transaction generation

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

Harris

-0.94

aii

-0.90

Miami

-0.89

 Amar

-0.87

Prince

-0.86

 âĸº

-0.85

rican

-0.84

 Haley

-0.84

 Chev

-0.83

orio

-0.81

POSITIVE LOGITS

Log

2.35

log

2.16

Log

2.08

LOG

2.02

log

2.02

 logs

1.85

 logging

1.83

 logger

1.78

LOG

1.77

 logged

1.56

Activations Density 0.240%

phrases related to logging and entries

terms related to logging and transaction generation

No Comments

No Known Activations