INDEX

Explanations

proper nouns or abbreviations related to political entities

oai_token-act-pair · gpt-3.5-turbo

references to a specific organization or entity, likely related to a regulatory body

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

 Alchemist

-0.86

swick

-0.82

ãĤ¤ãĥĪ

-0.73

ãĤ¨ãĥ«

-0.69

hold

-0.69

 Universities

-0.68

 Jericho

-0.67

mates

-0.67

lain

-0.67

gra

-0.67

POSITIVE LOGITS

FP

1.07

rint

1.01

ixel

0.96

olicy

0.94

unction

0.91

arser

0.89

requency

0.88

raction

0.87

odcast

0.86

conservancy

0.84

Activations Density 0.006%

proper nouns or abbreviations related to political entities

references to a specific organization or entity, likely related to a regulatory body

No Comments

No Known Activations