INDEX

Explanations

phrases related to a past time period or comparison to a previous state

oai_token-act-pair · gpt-3.5-turbo

comparisons of current states to past states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

sonian

-0.70

 Gorge

-0.62

oring

-0.61

 âĨ

-0.58

letters

-0.54

\\

-0.54

ERY

-0.53

 Griffin

-0.53

 liner

-0.51

 mediation

-0.51

POSITIVE LOGITS

 previously

0.78

 before

0.77

ufact

0.75

pec

0.74

 accustomed

0.73

 formerly

0.71

 originally

0.71

 prior

0.70

cells

0.69

 predecessors

0.69

Activations Density 0.164%

phrases related to a past time period or comparison to a previous state

comparisons of current states to past states

No Comments

No Known Activations