INDEX

Explanations

words related to the frequency or existence of various phenomena

oai_token-act-pair · gpt-3.5-turbo

terms related to prevalence and incidence rates of various conditions or events

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

iverse

-0.89

ebus

-0.88

erm

-0.78

imb

-0.77

 SECTION

-0.69

ottesville

-0.68

irgin

-0.68

paio

-0.68

 membr

-0.67

INTON

-0.67

POSITIVE LOGITS

 occurrence

0.90

 preval

0.84

 prevalence

0.84

 incidence

0.80

 rates

0.80

uating

0.75

uated

0.71

(%)

0.70

ality

0.70

 Rates

0.69

Activations Density 0.044%

words related to the frequency or existence of various phenomena

terms related to prevalence and incidence rates of various conditions or events

No Comments

No Known Activations