INDEX

Explanations

descriptions of traumatic events or crises

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 appro

-0.85

 lumber

-0.85

gru

-0.85

 repro

-0.83

tre

-0.82

pir

-0.80

 prelim

-0.79

 filib

-0.78

 ogre

-0.77

 unborn

-0.77

POSITIVE LOGITS

We

1.23

Unless

1.18

It

1.16

Without

1.15

There

1.15

They

1.13

Operation

1.12

Unfortunately

1.12

Our

1.11

Quite

1.11

Activations Density 0.134%

descriptions of traumatic events or crises

No Comments

No Known Activations