INDEX

Explanations

phrases related to consecutive actions or occurrences

oai_token-act-pair · gpt-3.5-turbo

phrases indicating consecutive or straight occurrences of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

isk

-0.82

lite

-0.72

fleet

-0.72

spoken

-0.71

adle

-0.71

lain

-0.70

hyde

-0.68

hod

-0.68

omics

-0.68

liness

-0.67

POSITIVE LOGITS

 digits

0.84

 consecutive

0.80

 summers

0.70

 uninterrupted

0.69

 victories

0.69

 year

0.68

 outing

0.67

 Earthqu

0.67

 weekends

0.67

 revisions

0.65

Activations Density 0.027%

phrases related to consecutive actions or occurrences

phrases indicating consecutive or straight occurrences of events

No Comments

No Known Activations