INDEX

Explanations

words related to financial or personal gains, particularly in the context of contracts or funds

oai_token-act-pair · gpt-3.5-turbo

references to benefits or advantages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ãĥĥãĥī

-0.73

Rim

-0.70

ãĥ£

-0.67

opic

-0.67

IPM

-0.66

bat

-0.66

WithNo

-0.66

swick

-0.64

parts

-0.63

wcsstore

-0.62

POSITIVE LOGITS

benefit

1.05

 conferred

1.04

 afforded

0.90

ocratic

0.90

 accrued

0.89

 claimants

0.86

 benefit

0.85

 outwe

0.83

ocracy

0.83

ocrats

0.82

Activations Density 0.028%

words related to financial or personal gains, particularly in the context of contracts or funds

references to benefits or advantages

No Comments

No Known Activations