INDEX

Explanations

The neuron is looking for references to concepts related to the term "Solid"

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Solid" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

llor

-0.77

cffffcc

-0.70

jo

-0.69

eur

-0.65

ulhu

-0.64

~~~~~~~~~~~~~~~~

-0.64

conservancy

-0.61

HAHA

-0.60

 waived

-0.60

joined

-0.60

POSITIVE LOGITS

GoldMagikarp

1.18

itary

1.15

arity

1.04

utonium

0.97

ified

0.84

atives

0.77

atio

0.77

ifying

0.76

 Snake

0.75

works

0.74

Activations Density 0.036%

The neuron is looking for references to concepts related to the term "Solid"

mentions of the term "Solid" in various contexts

No Comments

No Known Activations