INDEX

Explanations

statements made by different individuals in various contexts

oai_token-act-pair · gpt-3.5-turbo

instances of official statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avorite

-0.89

upiter

-0.85

cffff

-0.76

itals

-0.75

rys

-0.73

elsius

-0.69

juven

-0.67

ordinate

-0.67

aden

-0.66

 notor

-0.66

POSITIVE LOGITS

 statement

1.21

Statement

1.04

 statements

1.00

EMENT

0.90

soType

0.88

gow

0.86

 Statement

0.86

aires

0.84

 Statements

0.82

ements

0.78

Activations Density 0.027%

statements made by different individuals in various contexts

instances of official statements

No Comments

No Known Activations