INDEX

Explanations

phrases related to negative impacts or setbacks

oai_token-act-pair · gpt-3.5-turbo

phrases indicating negative impacts or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ript

-0.81

iosity

-0.68

RY

-0.67

uana

-0.67

cius

-0.67

 Malays

-0.67

ively

-0.65

phis

-0.63

âĸ¬

-0.62

ately

-0.62

POSITIVE LOGITS

hole

1.04

gun

0.93

holes

0.92

job

0.90

hard

0.90

pipe

0.88

blow

0.88

jobs

0.88

outs

0.87

waves

0.86

Activations Density 0.021%

phrases related to negative impacts or setbacks

phrases indicating negative impacts or consequences

No Comments

No Known Activations