INDEX

Explanations

terms related to political entities and actions

oai_token-act-pair · gpt-3.5-turbo

references to political candidates and potential impacts 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inately

-0.67

oxide

-0.65

enged

-0.65

 sadly

-0.64

Bench

-0.59

gio

-0.58

;;

-0.58

 Disabled

-0.57

 visibly

-0.56

 Kers

-0.55

POSITIVE LOGITS

arenthood

0.78

 sqor

0.75

zzle

0.72

rosso

0.71

 scenarios

0.69

ãĥĥãĥĪ

0.69

comings

0.69

SpaceEngineers

0.68

ãĥīãĥ©

0.67

ãĤ´ãĥ³

0.66

Activations Density 0.283%

terms related to political entities and actions

references to political candidates and potential impacts in various contexts

No Comments

No Known Activations