INDEX

Explanations

names of specific harbors

oai_token-act-pair · gpt-3.5-turbo

references to harbors and their significance

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

uable

-0.86

yson

-0.72

uv

-0.72

hesis

-0.71

iferation

-0.70

andr

-0.70

Downloadha

-0.70

oln

-0.70

ophers

-0.70

nesota

-0.69

POSITIVE LOGITS

 Harbor

0.85

 Ship

0.80

 Island

0.77

mallow

0.76

 Shore

0.74

 Harbour

0.74

 Islands

0.74

 Winds

0.73

 dwell

0.72

front

0.72

Activations Density 0.009%

names of specific harbors

references to harbors and their significance

No Comments

No Known Activations