INDEX

Explanations

rhetorical terms and phrases

oai_token-act-pair · gpt-3.5-turbo

terms related to rhetorical concepts and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nar

-0.80

ikarp

-0.77

wo

-0.75

spring

-0.72

net

-0.71

elsen

-0.70

nets

-0.70

YL

-0.69

iversity

-0.69

EMBER

-0.68

POSITIVE LOGITS

aukee

0.79

 bluff

0.77

 rebuke

0.75

 answ

0.74

 brid

0.68

 gesture

0.67

 halting

0.67

 hint

0.66

issance

0.66

 truce

0.66

Activations Density 0.100%

rhetorical terms and phrases

terms related to rhetorical concepts and their implications

No Comments

No Known Activations