INDEX

Explanations

words related to a specific organization or department within a larger entity

oai_token-act-pair · gpt-3.5-turbo

references to various departments within an organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

telling

-0.76

 sidx

-0.72

 Rounds

-0.68

 Instruments

-0.66

 Intent

-0.64

isin

-0.62

 Tone

-0.62

 Pose

-0.61

isers

-0.60

moving

-0.60

POSITIVE LOGITS

artment

0.98

alities

0.97

artments

0.96

ality

0.91

 departments

0.89

al

0.87

 secretaries

0.80

istry

0.78

ority

0.78

 manager

0.75

Activations Density 0.016%

words related to a specific organization or department within a larger entity

references to various departments within an organization

No Comments

No Known Activations