INDEX

Explanations

phrases containing the word "middle"

oai_token-act-pair · gpt-3.5-turbo

references to "the middle" 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 @ 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

cci

-0.73

orthy

-0.72

osponsors

-0.71

edIn

-0.69

illard

-0.68

ilings

-0.68

vec

-0.67

OUP

-0.67

utical

-0.65

atche

-0.65

POSITIVE LOGITS

stad

0.83

 layer

0.69

middle

0.67

lan

0.67

woods

0.66

piece

0.66

west

0.65

 lane

0.65

 middle

0.63

western

0.63

Activations Density 0.011%

phrases containing the word "middle"

references to "the middle" in various contexts

No Comments

No Known Activations