INDEX

Explanations

mentions of political figures, particularly senators

oai_token-act-pair · gpt-3.5-turbo

references to senators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 manual

-0.70

 Siberian

-0.67

 ponies

-0.66

 oper

-0.63

footed

-0.63

 unmarked

-0.62

 managerial

-0.61

LTD

-0.61

 hypers

-0.60

 civilisation

-0.59

POSITIVE LOGITS

iors

1.35

eca

1.05

pai

1.04

escent

1.02

esse

0.98

egal

0.96

olt

0.93

ority

0.90

ileaks

0.90

uary

0.89

Activations Density 0.011%

mentions of political figures, particularly senators

references to senators

No Comments

No Known Activations