INDEX

Explanations

instances of the word "suffer" and its variations

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

words related to experiencing negative consequences or hardships

oai_token-act-pair · gpt-3.5-turbo Triggered by @danbraun

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_slefr-ajt/2-res_slefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.2.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

runner

-0.95

wed

-0.93

law

-0.92

ipl

-0.89

runners

-0.87

sav

-0.86

ococ

-0.85

cle

-0.84

rouse

-0.83

reading

-0.83

POSITIVE LOGITS

 setbacks

1.01

owship

0.94

ospace

0.92

 dearly

0.90

senal

0.89

ansson

0.84

 Loss

0.84

 tremend

0.84

 adolesc

0.84

 endured

0.83

Activations Density 0.021%

instances of the word "suffer" and its variations

words related to experiencing negative consequences or hardships

No Comments

No Known Activations