INDEX

Explanations

dates or locations mentioned in a structured format

oai_token-act-pair · gpt-3.5-turbo

locations and events associated with leisure activities

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

naires

-0.64

 decoration

-0.62

 sten

-0.61

Ful

-0.61

 automotive

-0.60

 regular

-0.60

 pupp

-0.60

 mathemat

-0.60

Nib

-0.60

 demonstr

-0.59

POSITIVE LOGITS

Sensor

0.94

Status

0.93

Rating

0.89

Filename

0.86

Changes

0.84

Package

0.84

Price

0.83

Subject

0.81

Synopsis

0.81

Tags

0.81

Activations Density 0.258%

dates or locations mentioned in a structured format

locations and events associated with leisure activities

No Comments

No Known Activations