INDEX

Explanations

time-related expressions, specifically referring to past periods

oai_token-act-pair · gpt-3.5-turbo

temporal expressions related to durations, particularly years and months

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inav

-0.76

emort

-0.74

hett

-0.71

uctions

-0.71

ashtra

-0.71

atche

-0.68

acted

-0.65

 corridors

-0.63

estine

-0.63

ibaba

-0.61

POSITIVE LOGITS

ago

1.04

long

0.96

dozen

0.90

Ago

0.89

 apiece

0.85

night

0.75

glass

0.73

dream

0.72

nd

0.68

eteenth

0.67

Activations Density 0.089%

time-related expressions, specifically referring to past periods

temporal expressions related to durations, particularly years and months

No Comments

No Known Activations