INDEX

Explanations

statements made by individuals or entities

oai_token-act-pair · gpt-3.5-turbo

the word "saying" in various contexts, indicating reported speech or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

estern

-0.97

ammy

-0.89

visible

-0.74

peg

-0.74

erenn

-0.73

transfer

-0.72

ynam

-0.69

avorite

-0.69

ascus

-0.68

umbn

-0.67

POSITIVE LOGITS

"[

0.73

 they

0.70

it

0.66

 otherwise

0.65

"'

0.64

 "...

0.62

 pieces

0.61

"(

0.60

 goodbye

0.60

 Niet

0.60

Activations Density 0.075%

statements made by individuals or entities

the word "saying" in various contexts, indicating reported speech or statements

No Comments

No Known Activations