INDEX

Explanations

references to organizational positions of authority, particularly those related to businesses or institutions

oai_token-act-pair · gpt-3.5-turbo

repeated references to a specific position or role

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

é¾

-0.91

dayName

-0.80

nces

-0.74

æĺ

-0.74

 externalToEVAOnly

-0.74

-0.70

fml

-0.68

edu

-0.68

 Cosponsors

-0.68

theless

-0.68

POSITIVE LOGITS

 overseeing

0.75

ovie

0.73

thood

0.68

 negotiator

0.64

jury

0.62

owitz

0.62

ovy

0.61

ceptor

0.61

rency

0.61

 Winston

0.60

Activations Density 0.073%

references to organizational positions of authority, particularly those related to businesses or institutions

repeated references to a specific position or role

No Comments

No Known Activations