INDEX

Explanations

phrases related to the future or progression over time

oai_token-act-pair · gpt-3.5-turbo

references to 'the road' in various contexts

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

emort

-0.87

 Socket

-0.74

abilia

-0.70

ermott

-0.70

ancial

-0.69

achusetts

-0.68

encies

-0.68

teness

-0.68

Dat

-0.67

andum

-0.67

POSITIVE LOGITS

trip

0.98

lane

0.86

block

0.84

ways

0.83

cycle

0.82

runner

0.80

fare

0.78

side

0.78

 road

0.76

blocks

0.76

Activations Density 0.014%

phrases related to the future or progression over time

references to 'the road' in various contexts

No Comments

No Known Activations