INDEX

Explanations

words related to consideration, judgment, or assessment

oai_token-act-pair · gpt-3.5-turbo

terms related to evaluations and judgments 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

yrinth

-0.77

ICLE

-0.77

hemy

-0.76

chell

-0.76

uras

-0.73

lav

-0.70

idity

-0.69

ured

-0.68

NetMessage

-0.67

uve

-0.67

POSITIVE LOGITS

apter

0.76

 GOODMAN

0.74

ÅĤ

0.73

 reckoned

0.73

ODUCT

0.71

payers

0.71

restling

0.68

puter

0.68

ashington

0.66

ailable

0.65

Activations Density 0.021%

words related to consideration, judgment, or assessment

terms related to evaluations and judgments in various contexts

No Comments

No Known Activations