INDEX

Explanations

mentions or discussions about a specific product feature

oai_token-act-pair · gpt-3.5-turbo

mentions of features in various contexts

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

sis

-0.82

azar

-0.77

apy

-0.74

usable

-0.72

uter

-0.72

si

-0.71

aline

-0.67

 millenn

-0.66

umeric

-0.66

 exting

-0.65

POSITIVE LOGITS

Feature

1.06

 features

0.99

features

0.95

 prominently

0.92

 Features

0.92

Features

0.92

feature

0.91

ttes

0.90

lich

0.83

 feature

0.80

Activations Density 0.015%

mentions or discussions about a specific product feature

mentions of features in various contexts

No Comments

No Known Activations