INDEX

Explanations

words related to legal and political entities

oai_token-act-pair · gpt-3.5-turbo

instances of numerical values and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

yrics

-0.77

Random

-0.75

INESS

-0.72

Choice

-0.72

SIGN

-0.71

etary

-0.70

agan

-0.69

Dir

-0.68

POSE

-0.67

ADVERTISEMENT

-0.66

POSITIVE LOGITS

 helicop

0.84

ashtra

0.79

 ashore

0.68

 stricken

0.64

nsics

0.61

withstanding

0.61

 wrestling

0.60

borgh

0.60

theless

0.59

 convol

0.58

Activations Density 0.000%

words related to legal and political entities

instances of numerical values and their contexts

No Comments

No Known Activations