INDEX

Explanations

references to lakes and their related features

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

references to specific bodies of water, particularly lakes

oai_token-act-pair · gpt-3.5-turbo

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

CLASSIFIED

-0.88

ENTS

-0.76

ulate

-0.73

nesday

-0.71

imental

-0.69

ENT

-0.69

IRED

-0.67

 tremend

-0.67

ifiable

-0.65

psons

-0.65

POSITIVE LOGITS

 Erie

0.93

 ponds

0.93

 lakes

0.92

 lake

0.91

 basin

0.89

front

0.88

weed

0.85

tub

0.85

 reservoir

0.85

ids

0.81

Activations Density 0.016%

references to lakes and their related features

references to specific bodies of water, particularly lakes

No Comments

No Known Activations