INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to specific individuals, places, or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Âł Âł Âł Âł

-0.84

doi

-0.75

 Mehran

-0.71

hip

-0.70

heet

-0.69

ORT

-0.68

cript

-0.68

rison

-0.68

 æľ

-0.67

hips

-0.67

POSITIVE LOGITS

's

1.13

istic

0.74

eto

0.67

 experien

0.65

 Enterprises

0.64

staking

0.64

omics

0.61

 contrace

0.61

osaurus

0.61

 Smile

0.61

Activations Density 0.171%

proper nouns or names

proper nouns related to specific individuals, places, or entities

No Comments

No Known Activations