INDEX

Explanations

phrases or sentences related to detailed statements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "statement."

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

bid

-0.78

rys

-0.77

MpServer

-0.75

itals

-0.72

elsius

-0.72

Friend

-0.72

rowd

-0.71

osponsors

-0.67

cffff

-0.67

versely

-0.67

POSITIVE LOGITS

 statements

0.88

ariat

0.83

 pronoun

0.81

 uttered

0.81

gow

0.81

 statement

0.80

ARB

0.78

 regarding

0.74

 unequivocally

0.73

Statement

0.72

Activations Density 0.030%

phrases or sentences related to detailed statements

occurrences of the word "statement."

No Comments

No Known Activations