INDEX

Explanations

expressions of personal memories or recollections

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

memories or recollections described in past tense

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ÃŁ

-0.79

oit

-0.78

tan

-0.76

assi

-0.75

adh

-0.73

acies

-0.73

alach

-0.71

ahime

-0.69

otomy

-0.69

pex

-0.68

POSITIVE LOGITS

 vividly

1.08

remember

0.97

 remembering

0.96

 recalling

0.90

 recollection

0.87

 nostalg

0.86

 remembered

0.84

 Memories

0.83

 memories

0.83

 Remem

0.82

Activations Density 0.023%

expressions of personal memories or recollections

memories or recollections described in past tense

No Comments

No Known Activations