INDEX

Explanations

adjectives describing trustworthiness and dependability

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to reliability and trustworthiness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

aeper

-0.83

ovember

-0.82

ften

-0.79

ophy

-0.76

kay

-0.74

ylum

-0.74

osphere

-0.74

thur

-0.72

eanor

-0.72

poses

-0.72

POSITIVE LOGITS

 reliable

1.05

 narrator

1.04

 source

0.91

 sources

0.89

 trustworthy

0.83

iability

0.83

 reliability

0.83

 unreliable

0.80

 isot

0.78

 indicator

0.77

Activations Density 0.070%

adjectives describing trustworthiness and dependability

terms and phrases related to reliability and trustworthiness

No Comments

No Known Activations