INDEX

Explanations

phrases referring to past states or previous conditions

oai_token-act-pair · gpt-3.5-turbo

references to time, specifically indicating past conditions or states

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

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

asso

-0.76

agent

-0.74

anders

-0.74

rics

-0.73

aby

-0.72

ighter

-0.71

vez

-0.70

anche

-0.70

ento

-0.70

atro

-0.69

POSITIVE LOGITS

Era

0.78

era

0.74

 incarn

0.73

 fashioned

0.72

 thriving

0.69

 forb

0.69

 defunct

0.68

 incarnation

0.68

 eras

0.68

 precedent

0.68

Activations Density 0.277%

phrases referring to past states or previous conditions

references to time, specifically indicating past conditions or states

No Comments

No Known Activations